| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 3, | |
| "global_step": 141, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06382978723404255, | |
| "grad_norm": 134.82960510253906, | |
| "learning_rate": 3.4524225370179614e-06, | |
| "loss": 2.0515, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06382978723404255, | |
| "eval_loss": 1.1583281755447388, | |
| "eval_runtime": 97.0528, | |
| "eval_samples_per_second": 3.091, | |
| "eval_steps_per_second": 0.103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 141.0943145751953, | |
| "learning_rate": 3.377369873169745e-06, | |
| "loss": 1.5004, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "eval_loss": 1.1162742376327515, | |
| "eval_runtime": 60.2202, | |
| "eval_samples_per_second": 4.982, | |
| "eval_steps_per_second": 0.166, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19148936170212766, | |
| "grad_norm": 134.9931640625, | |
| "learning_rate": 3.3023172093215284e-06, | |
| "loss": 1.5627, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19148936170212766, | |
| "eval_loss": 1.0802254676818848, | |
| "eval_runtime": 41.4969, | |
| "eval_samples_per_second": 7.229, | |
| "eval_steps_per_second": 0.241, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "grad_norm": 113.67478942871094, | |
| "learning_rate": 3.227264545473312e-06, | |
| "loss": 1.3625, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2553191489361702, | |
| "eval_loss": 1.0606831312179565, | |
| "eval_runtime": 41.3217, | |
| "eval_samples_per_second": 7.26, | |
| "eval_steps_per_second": 0.242, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3191489361702128, | |
| "grad_norm": 105.70118713378906, | |
| "learning_rate": 3.152211881625095e-06, | |
| "loss": 1.6648, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3191489361702128, | |
| "eval_loss": 1.0375689268112183, | |
| "eval_runtime": 48.7659, | |
| "eval_samples_per_second": 6.152, | |
| "eval_steps_per_second": 0.205, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3829787234042553, | |
| "grad_norm": 96.33596801757812, | |
| "learning_rate": 3.077159217776879e-06, | |
| "loss": 1.3305, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3829787234042553, | |
| "eval_loss": 1.0117995738983154, | |
| "eval_runtime": 41.5605, | |
| "eval_samples_per_second": 7.218, | |
| "eval_steps_per_second": 0.241, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.44680851063829785, | |
| "grad_norm": 105.89424133300781, | |
| "learning_rate": 3.002106553928662e-06, | |
| "loss": 1.2195, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.44680851063829785, | |
| "eval_loss": 0.9878906011581421, | |
| "eval_runtime": 44.9672, | |
| "eval_samples_per_second": 6.672, | |
| "eval_steps_per_second": 0.222, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": 96.90633392333984, | |
| "learning_rate": 2.9270538900804454e-06, | |
| "loss": 1.4076, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "eval_loss": 0.9666847586631775, | |
| "eval_runtime": 52.2922, | |
| "eval_samples_per_second": 5.737, | |
| "eval_steps_per_second": 0.191, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.574468085106383, | |
| "grad_norm": 101.37423706054688, | |
| "learning_rate": 2.852001226232229e-06, | |
| "loss": 1.5353, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.574468085106383, | |
| "eval_loss": 0.9519509077072144, | |
| "eval_runtime": 41.7527, | |
| "eval_samples_per_second": 7.185, | |
| "eval_steps_per_second": 0.24, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "grad_norm": 92.97295379638672, | |
| "learning_rate": 2.7769485623840124e-06, | |
| "loss": 1.2954, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6382978723404256, | |
| "eval_loss": 0.937315046787262, | |
| "eval_runtime": 41.2373, | |
| "eval_samples_per_second": 7.275, | |
| "eval_steps_per_second": 0.242, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7021276595744681, | |
| "grad_norm": 110.28973388671875, | |
| "learning_rate": 2.701895898535796e-06, | |
| "loss": 1.489, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7021276595744681, | |
| "eval_loss": 0.9187784790992737, | |
| "eval_runtime": 42.0237, | |
| "eval_samples_per_second": 7.139, | |
| "eval_steps_per_second": 0.238, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "grad_norm": 93.82958984375, | |
| "learning_rate": 2.6268432346875793e-06, | |
| "loss": 1.5987, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7659574468085106, | |
| "eval_loss": 0.9012949466705322, | |
| "eval_runtime": 41.6757, | |
| "eval_samples_per_second": 7.198, | |
| "eval_steps_per_second": 0.24, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8297872340425532, | |
| "grad_norm": 74.33155822753906, | |
| "learning_rate": 2.551790570839363e-06, | |
| "loss": 1.3207, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8297872340425532, | |
| "eval_loss": 0.8868340849876404, | |
| "eval_runtime": 41.5644, | |
| "eval_samples_per_second": 7.218, | |
| "eval_steps_per_second": 0.241, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8936170212765957, | |
| "grad_norm": 100.4666519165039, | |
| "learning_rate": 2.4767379069911463e-06, | |
| "loss": 1.3121, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8936170212765957, | |
| "eval_loss": 0.8769957423210144, | |
| "eval_runtime": 51.3924, | |
| "eval_samples_per_second": 5.837, | |
| "eval_steps_per_second": 0.195, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9574468085106383, | |
| "grad_norm": 78.03990173339844, | |
| "learning_rate": 2.4016852431429298e-06, | |
| "loss": 1.198, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9574468085106383, | |
| "eval_loss": 0.8720031976699829, | |
| "eval_runtime": 41.262, | |
| "eval_samples_per_second": 7.271, | |
| "eval_steps_per_second": 0.242, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "grad_norm": 48.33544158935547, | |
| "learning_rate": 2.326632579294713e-06, | |
| "loss": 1.0786, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0212765957446808, | |
| "eval_loss": 0.8655586838722229, | |
| "eval_runtime": 41.5498, | |
| "eval_samples_per_second": 7.22, | |
| "eval_steps_per_second": 0.241, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0851063829787233, | |
| "grad_norm": 35.39493179321289, | |
| "learning_rate": 2.2515799154464967e-06, | |
| "loss": 0.7367, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.0851063829787233, | |
| "eval_loss": 0.8586752414703369, | |
| "eval_runtime": 47.8744, | |
| "eval_samples_per_second": 6.266, | |
| "eval_steps_per_second": 0.209, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.148936170212766, | |
| "grad_norm": 38.954620361328125, | |
| "learning_rate": 2.17652725159828e-06, | |
| "loss": 0.5906, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.148936170212766, | |
| "eval_loss": 0.854831874370575, | |
| "eval_runtime": 41.7553, | |
| "eval_samples_per_second": 7.185, | |
| "eval_steps_per_second": 0.239, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.2127659574468086, | |
| "grad_norm": 61.59217071533203, | |
| "learning_rate": 2.1014745877500633e-06, | |
| "loss": 0.794, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.2127659574468086, | |
| "eval_loss": 0.8518243432044983, | |
| "eval_runtime": 41.3107, | |
| "eval_samples_per_second": 7.262, | |
| "eval_steps_per_second": 0.242, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": 43.460899353027344, | |
| "learning_rate": 2.026421923901847e-06, | |
| "loss": 0.6699, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "eval_loss": 0.849520742893219, | |
| "eval_runtime": 41.3487, | |
| "eval_samples_per_second": 7.255, | |
| "eval_steps_per_second": 0.242, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.3404255319148937, | |
| "grad_norm": 40.51012420654297, | |
| "learning_rate": 1.9513692600536303e-06, | |
| "loss": 0.5351, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.3404255319148937, | |
| "eval_loss": 0.8519204258918762, | |
| "eval_runtime": 41.2821, | |
| "eval_samples_per_second": 7.267, | |
| "eval_steps_per_second": 0.242, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.4042553191489362, | |
| "grad_norm": 55.731903076171875, | |
| "learning_rate": 1.8763165962054137e-06, | |
| "loss": 0.6526, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.4042553191489362, | |
| "eval_loss": 0.85467129945755, | |
| "eval_runtime": 41.1797, | |
| "eval_samples_per_second": 7.285, | |
| "eval_steps_per_second": 0.243, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.4680851063829787, | |
| "grad_norm": 55.70009231567383, | |
| "learning_rate": 1.801263932357197e-06, | |
| "loss": 0.7753, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.4680851063829787, | |
| "eval_loss": 0.8556016087532043, | |
| "eval_runtime": 41.2215, | |
| "eval_samples_per_second": 7.278, | |
| "eval_steps_per_second": 0.243, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.5319148936170213, | |
| "grad_norm": 51.552974700927734, | |
| "learning_rate": 1.7262112685089807e-06, | |
| "loss": 0.6996, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.5319148936170213, | |
| "eval_loss": 0.8541069626808167, | |
| "eval_runtime": 41.8446, | |
| "eval_samples_per_second": 7.169, | |
| "eval_steps_per_second": 0.239, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": 61.95724105834961, | |
| "learning_rate": 1.6511586046607642e-06, | |
| "loss": 0.8078, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "eval_loss": 0.8522682785987854, | |
| "eval_runtime": 45.1234, | |
| "eval_samples_per_second": 6.648, | |
| "eval_steps_per_second": 0.222, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.6595744680851063, | |
| "grad_norm": 51.09059524536133, | |
| "learning_rate": 1.5761059408125475e-06, | |
| "loss": 0.6704, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.6595744680851063, | |
| "eval_loss": 0.8499072194099426, | |
| "eval_runtime": 41.6072, | |
| "eval_samples_per_second": 7.21, | |
| "eval_steps_per_second": 0.24, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.7234042553191489, | |
| "grad_norm": 57.01670455932617, | |
| "learning_rate": 1.501053276964331e-06, | |
| "loss": 0.5976, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.7234042553191489, | |
| "eval_loss": 0.8474313616752625, | |
| "eval_runtime": 41.405, | |
| "eval_samples_per_second": 7.246, | |
| "eval_steps_per_second": 0.242, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.7872340425531914, | |
| "grad_norm": 58.575130462646484, | |
| "learning_rate": 1.4260006131161144e-06, | |
| "loss": 0.6588, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.7872340425531914, | |
| "eval_loss": 0.8449164032936096, | |
| "eval_runtime": 41.6188, | |
| "eval_samples_per_second": 7.208, | |
| "eval_steps_per_second": 0.24, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.851063829787234, | |
| "grad_norm": 60.291622161865234, | |
| "learning_rate": 1.350947949267898e-06, | |
| "loss": 0.7081, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.851063829787234, | |
| "eval_loss": 0.8420330882072449, | |
| "eval_runtime": 41.9537, | |
| "eval_samples_per_second": 7.151, | |
| "eval_steps_per_second": 0.238, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.9148936170212765, | |
| "grad_norm": 50.23271942138672, | |
| "learning_rate": 1.2758952854196814e-06, | |
| "loss": 0.5632, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9148936170212765, | |
| "eval_loss": 0.8388514518737793, | |
| "eval_runtime": 41.6015, | |
| "eval_samples_per_second": 7.211, | |
| "eval_steps_per_second": 0.24, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.978723404255319, | |
| "grad_norm": 52.8415412902832, | |
| "learning_rate": 1.2008426215714649e-06, | |
| "loss": 0.6249, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.978723404255319, | |
| "eval_loss": 0.8353903293609619, | |
| "eval_runtime": 41.6241, | |
| "eval_samples_per_second": 7.207, | |
| "eval_steps_per_second": 0.24, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 2.0425531914893615, | |
| "grad_norm": 55.50529098510742, | |
| "learning_rate": 1.1257899577232484e-06, | |
| "loss": 0.612, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.0425531914893615, | |
| "eval_loss": 0.8322966694831848, | |
| "eval_runtime": 41.6827, | |
| "eval_samples_per_second": 7.197, | |
| "eval_steps_per_second": 0.24, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.106382978723404, | |
| "grad_norm": 33.535972595214844, | |
| "learning_rate": 1.0507372938750316e-06, | |
| "loss": 0.4171, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.106382978723404, | |
| "eval_loss": 0.8299477100372314, | |
| "eval_runtime": 41.6454, | |
| "eval_samples_per_second": 7.204, | |
| "eval_steps_per_second": 0.24, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.1702127659574466, | |
| "grad_norm": 33.902915954589844, | |
| "learning_rate": 9.756846300268151e-07, | |
| "loss": 0.3473, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.1702127659574466, | |
| "eval_loss": 0.8301065564155579, | |
| "eval_runtime": 41.3799, | |
| "eval_samples_per_second": 7.25, | |
| "eval_steps_per_second": 0.242, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.2340425531914896, | |
| "grad_norm": 54.96790313720703, | |
| "learning_rate": 9.006319661785985e-07, | |
| "loss": 0.4751, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.2340425531914896, | |
| "eval_loss": 0.8314597606658936, | |
| "eval_runtime": 41.4767, | |
| "eval_samples_per_second": 7.233, | |
| "eval_steps_per_second": 0.241, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.297872340425532, | |
| "grad_norm": 43.61612319946289, | |
| "learning_rate": 8.255793023303821e-07, | |
| "loss": 0.4088, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.297872340425532, | |
| "eval_loss": 0.8334099054336548, | |
| "eval_runtime": 60.1786, | |
| "eval_samples_per_second": 4.985, | |
| "eval_steps_per_second": 0.166, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.3617021276595747, | |
| "grad_norm": 41.3808708190918, | |
| "learning_rate": 7.505266384821655e-07, | |
| "loss": 0.3174, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.3617021276595747, | |
| "eval_loss": 0.8363153338432312, | |
| "eval_runtime": 41.6562, | |
| "eval_samples_per_second": 7.202, | |
| "eval_steps_per_second": 0.24, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.425531914893617, | |
| "grad_norm": 39.414100646972656, | |
| "learning_rate": 6.75473974633949e-07, | |
| "loss": 0.3267, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.425531914893617, | |
| "eval_loss": 0.8386973142623901, | |
| "eval_runtime": 41.5441, | |
| "eval_samples_per_second": 7.221, | |
| "eval_steps_per_second": 0.241, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.4893617021276597, | |
| "grad_norm": 41.55443572998047, | |
| "learning_rate": 6.004213107857324e-07, | |
| "loss": 0.3142, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.4893617021276597, | |
| "eval_loss": 0.8412825465202332, | |
| "eval_runtime": 41.7129, | |
| "eval_samples_per_second": 7.192, | |
| "eval_steps_per_second": 0.24, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": 45.54193115234375, | |
| "learning_rate": 5.253686469375158e-07, | |
| "loss": 0.4253, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "eval_loss": 0.8432453274726868, | |
| "eval_runtime": 41.5872, | |
| "eval_samples_per_second": 7.214, | |
| "eval_steps_per_second": 0.24, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.617021276595745, | |
| "grad_norm": 58.93795394897461, | |
| "learning_rate": 4.5031598308929925e-07, | |
| "loss": 0.4269, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.617021276595745, | |
| "eval_loss": 0.8454075455665588, | |
| "eval_runtime": 41.7045, | |
| "eval_samples_per_second": 7.193, | |
| "eval_steps_per_second": 0.24, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.6808510638297873, | |
| "grad_norm": 30.54688835144043, | |
| "learning_rate": 3.7526331924108274e-07, | |
| "loss": 0.2765, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.6808510638297873, | |
| "eval_loss": 0.8469324707984924, | |
| "eval_runtime": 41.6321, | |
| "eval_samples_per_second": 7.206, | |
| "eval_steps_per_second": 0.24, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.74468085106383, | |
| "grad_norm": 46.656986236572266, | |
| "learning_rate": 3.002106553928662e-07, | |
| "loss": 0.3071, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.74468085106383, | |
| "eval_loss": 0.848118782043457, | |
| "eval_runtime": 41.3133, | |
| "eval_samples_per_second": 7.262, | |
| "eval_steps_per_second": 0.242, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.8085106382978724, | |
| "grad_norm": 41.179161071777344, | |
| "learning_rate": 2.2515799154464963e-07, | |
| "loss": 0.3277, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.8085106382978724, | |
| "eval_loss": 0.8486995100975037, | |
| "eval_runtime": 41.4208, | |
| "eval_samples_per_second": 7.243, | |
| "eval_steps_per_second": 0.241, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.872340425531915, | |
| "grad_norm": 35.64809036254883, | |
| "learning_rate": 1.501053276964331e-07, | |
| "loss": 0.3206, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.872340425531915, | |
| "eval_loss": 0.8487841486930847, | |
| "eval_runtime": 41.4922, | |
| "eval_samples_per_second": 7.23, | |
| "eval_steps_per_second": 0.241, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.9361702127659575, | |
| "grad_norm": 39.29479217529297, | |
| "learning_rate": 7.505266384821656e-08, | |
| "loss": 0.4095, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.9361702127659575, | |
| "eval_loss": 0.848578929901123, | |
| "eval_runtime": 41.4984, | |
| "eval_samples_per_second": 7.229, | |
| "eval_steps_per_second": 0.241, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 37.54413604736328, | |
| "learning_rate": 0.0, | |
| "loss": 0.2987, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.8485209941864014, | |
| "eval_runtime": 41.5472, | |
| "eval_samples_per_second": 7.221, | |
| "eval_steps_per_second": 0.241, | |
| "step": 141 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 141, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 523328480700102.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": { | |
| "_wandb": {}, | |
| "assignments": {}, | |
| "decay": 0.1, | |
| "learning_rate": 3.527475200866178e-06, | |
| "metric": "eval/loss", | |
| "per_device_train_batch_size": 64 | |
| } | |
| } | |