| { | |
| "best_metric": 0.2728331387042999, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.3917727717923604, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0039177277179236044, | |
| "grad_norm": 35.1519660949707, | |
| "learning_rate": 1e-05, | |
| "loss": 3.3377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0039177277179236044, | |
| "eval_loss": 1.376975655555725, | |
| "eval_runtime": 30.7914, | |
| "eval_samples_per_second": 13.965, | |
| "eval_steps_per_second": 3.507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007835455435847209, | |
| "grad_norm": 37.591468811035156, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5823, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011753183153770812, | |
| "grad_norm": 27.038301467895508, | |
| "learning_rate": 3e-05, | |
| "loss": 3.1019, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015670910871694418, | |
| "grad_norm": 17.632797241210938, | |
| "learning_rate": 4e-05, | |
| "loss": 2.424, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019588638589618023, | |
| "grad_norm": 13.900057792663574, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7934, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023506366307541625, | |
| "grad_norm": 6.731367111206055, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5624, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02742409402546523, | |
| "grad_norm": 4.34248161315918, | |
| "learning_rate": 7e-05, | |
| "loss": 1.2948, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.031341821743388835, | |
| "grad_norm": 3.769124746322632, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3975, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03525954946131244, | |
| "grad_norm": 3.391641855239868, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2989, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.039177277179236046, | |
| "grad_norm": 3.0701184272766113, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0842, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.043095004897159644, | |
| "grad_norm": 3.9934017658233643, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.0914, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04701273261508325, | |
| "grad_norm": 3.2494006156921387, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.1219, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.050930460333006855, | |
| "grad_norm": 3.7557196617126465, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.1797, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05484818805093046, | |
| "grad_norm": 3.097635507583618, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.215, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.058765915768854066, | |
| "grad_norm": 3.3909478187561035, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.0895, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06268364348677767, | |
| "grad_norm": 3.7466847896575928, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.3652, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06660137120470128, | |
| "grad_norm": 3.1385905742645264, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.1725, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07051909892262488, | |
| "grad_norm": 3.1092734336853027, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.3138, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07443682664054849, | |
| "grad_norm": 2.706139326095581, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.0156, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07835455435847209, | |
| "grad_norm": 3.3206448554992676, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.3558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08227228207639568, | |
| "grad_norm": 2.7940611839294434, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.2443, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08619000979431929, | |
| "grad_norm": 2.728489875793457, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.1225, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0901077375122429, | |
| "grad_norm": 2.7424354553222656, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.118, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0940254652301665, | |
| "grad_norm": 2.959437847137451, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.1265, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0979431929480901, | |
| "grad_norm": 3.068791151046753, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.111, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10186092066601371, | |
| "grad_norm": 3.436812400817871, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.2612, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10577864838393732, | |
| "grad_norm": 2.8119099140167236, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.9175, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10969637610186092, | |
| "grad_norm": 2.9515905380249023, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.1611, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11361410381978453, | |
| "grad_norm": 3.0629842281341553, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.0789, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11753183153770813, | |
| "grad_norm": 3.72255277633667, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.1929, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12144955925563174, | |
| "grad_norm": 2.680954694747925, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.9458, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12536728697355534, | |
| "grad_norm": 2.4375383853912354, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.949, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12928501469147893, | |
| "grad_norm": 2.8537662029266357, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.1638, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13320274240940255, | |
| "grad_norm": 2.751599073410034, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.1644, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13712047012732614, | |
| "grad_norm": 2.9511516094207764, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.052, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14103819784524976, | |
| "grad_norm": 2.903895616531372, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.0966, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14495592556317335, | |
| "grad_norm": 2.5975160598754883, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.033, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14887365328109697, | |
| "grad_norm": 2.664412021636963, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.1325, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15279138099902057, | |
| "grad_norm": 2.3869800567626953, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.8831, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15670910871694418, | |
| "grad_norm": 3.5770905017852783, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.0356, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16062683643486778, | |
| "grad_norm": 3.232245922088623, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.1462, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16454456415279137, | |
| "grad_norm": 2.72615647315979, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.0273, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.168462291870715, | |
| "grad_norm": 2.8978590965270996, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.021, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17238001958863858, | |
| "grad_norm": 3.248000144958496, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.093, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1762977473065622, | |
| "grad_norm": 2.8521573543548584, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.0163, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1802154750244858, | |
| "grad_norm": 3.390756845474243, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.8542, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1841332027424094, | |
| "grad_norm": 2.9699442386627197, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.9035, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.188050930460333, | |
| "grad_norm": 2.9843027591705322, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.0058, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19196865817825662, | |
| "grad_norm": 4.668224334716797, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.7376, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1958863858961802, | |
| "grad_norm": 2.9681031703948975, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.7555, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1958863858961802, | |
| "eval_loss": 0.3203987777233124, | |
| "eval_runtime": 31.553, | |
| "eval_samples_per_second": 13.628, | |
| "eval_steps_per_second": 3.423, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19980411361410383, | |
| "grad_norm": 7.285029888153076, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 1.5949, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.20372184133202742, | |
| "grad_norm": 4.377089500427246, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 1.3685, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.20763956904995104, | |
| "grad_norm": 2.7384912967681885, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 1.329, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.21155729676787463, | |
| "grad_norm": 2.206838846206665, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 1.1793, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.21547502448579825, | |
| "grad_norm": 2.329073905944824, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 1.0442, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.21939275220372184, | |
| "grad_norm": 2.0647895336151123, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.0533, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.22331047992164543, | |
| "grad_norm": 2.3976070880889893, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 1.1446, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.22722820763956905, | |
| "grad_norm": 2.5454862117767334, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.2031, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.23114593535749264, | |
| "grad_norm": 2.18048357963562, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 1.2731, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.23506366307541626, | |
| "grad_norm": 2.0146234035491943, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.1083, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.23898139079333985, | |
| "grad_norm": 2.171734094619751, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.9576, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.24289911851126347, | |
| "grad_norm": 2.0504679679870605, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 1.1194, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.24681684622918706, | |
| "grad_norm": 2.211573362350464, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 1.0986, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.2507345739471107, | |
| "grad_norm": 2.2392194271087646, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 1.1292, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.2546523016650343, | |
| "grad_norm": 2.342341661453247, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 1.1437, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.25857002938295787, | |
| "grad_norm": 2.102189064025879, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 1.0247, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2624877571008815, | |
| "grad_norm": 2.1631100177764893, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 1.0929, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2664054848188051, | |
| "grad_norm": 2.0671801567077637, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 1.1522, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2703232125367287, | |
| "grad_norm": 2.249319314956665, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 1.0299, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2742409402546523, | |
| "grad_norm": 2.0861968994140625, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.9798, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2781586679725759, | |
| "grad_norm": 2.284118890762329, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.9014, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2820763956904995, | |
| "grad_norm": 2.335890054702759, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.9852, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.2859941234084231, | |
| "grad_norm": 2.15493106842041, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 1.024, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2899118511263467, | |
| "grad_norm": 2.6023154258728027, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 1.134, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2938295788442703, | |
| "grad_norm": 2.412675142288208, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 1.1444, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.29774730656219395, | |
| "grad_norm": 2.2884745597839355, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 1.0542, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.30166503428011754, | |
| "grad_norm": 2.557800531387329, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 1.3114, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.30558276199804113, | |
| "grad_norm": 2.212139129638672, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 1.0496, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.3095004897159647, | |
| "grad_norm": 2.3875274658203125, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 1.1647, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.31341821743388837, | |
| "grad_norm": 2.358973979949951, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.9839, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.31733594515181196, | |
| "grad_norm": 2.8181726932525635, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 1.17, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.32125367286973555, | |
| "grad_norm": 2.4572412967681885, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.9679, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.32517140058765914, | |
| "grad_norm": 2.355374574661255, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.9826, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.32908912830558273, | |
| "grad_norm": 2.5143699645996094, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 1.1583, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.3330068560235064, | |
| "grad_norm": 2.4585354328155518, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.9229, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.33692458374143, | |
| "grad_norm": 3.429137706756592, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.8921, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.34084231145935356, | |
| "grad_norm": 2.3490748405456543, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.9492, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.34476003917727716, | |
| "grad_norm": 2.655750036239624, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.9217, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.3486777668952008, | |
| "grad_norm": 2.411027193069458, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.8969, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.3525954946131244, | |
| "grad_norm": 2.8227200508117676, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 1.2383, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.356513222331048, | |
| "grad_norm": 2.5691335201263428, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 1.0072, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.3604309500489716, | |
| "grad_norm": 2.5621490478515625, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 1.0163, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.3643486777668952, | |
| "grad_norm": 2.4902713298797607, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.9825, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.3682664054848188, | |
| "grad_norm": 2.6015195846557617, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 1.0142, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.3721841332027424, | |
| "grad_norm": 2.901930093765259, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 1.0073, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.376101860920666, | |
| "grad_norm": 2.4084105491638184, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.87, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.38001958863858964, | |
| "grad_norm": 2.4517323970794678, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.8646, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.38393731635651324, | |
| "grad_norm": 2.4089605808258057, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.7959, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.3878550440744368, | |
| "grad_norm": 2.4464828968048096, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.6847, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3917727717923604, | |
| "grad_norm": 3.361382484436035, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.8682, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3917727717923604, | |
| "eval_loss": 0.2728331387042999, | |
| "eval_runtime": 31.565, | |
| "eval_samples_per_second": 13.623, | |
| "eval_steps_per_second": 3.422, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.431616484278272e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |