| { | |
| "best_metric": 0.26534104347229004, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.27012617735916117, | |
| "eval_steps": 25, | |
| "global_step": 95, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0028434334458859074, | |
| "grad_norm": 22.599037170410156, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 5.3378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0028434334458859074, | |
| "eval_loss": 5.232264995574951, | |
| "eval_runtime": 3.9625, | |
| "eval_samples_per_second": 12.618, | |
| "eval_steps_per_second": 3.281, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005686866891771815, | |
| "grad_norm": 23.47909164428711, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 5.2597, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008530300337657722, | |
| "grad_norm": 18.171615600585938, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3128, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01137373378354363, | |
| "grad_norm": 14.74112606048584, | |
| "learning_rate": 9.997376600647783e-05, | |
| "loss": 2.5084, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014217167229429535, | |
| "grad_norm": 11.828715324401855, | |
| "learning_rate": 9.989509461357426e-05, | |
| "loss": 1.0016, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017060600675315445, | |
| "grad_norm": 2.351505756378174, | |
| "learning_rate": 9.976407754861426e-05, | |
| "loss": 0.4414, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019904034121201352, | |
| "grad_norm": 5.641177177429199, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.4406, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02274746756708726, | |
| "grad_norm": 2.2351808547973633, | |
| "learning_rate": 9.934567829727386e-05, | |
| "loss": 0.3914, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.025590901012973163, | |
| "grad_norm": 2.748798131942749, | |
| "learning_rate": 9.905878394570453e-05, | |
| "loss": 0.3943, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02843433445885907, | |
| "grad_norm": 2.5455727577209473, | |
| "learning_rate": 9.872051902290737e-05, | |
| "loss": 0.378, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03127776790474498, | |
| "grad_norm": 3.8824398517608643, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.4721, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03412120135063089, | |
| "grad_norm": 3.543416976928711, | |
| "learning_rate": 9.789151450663723e-05, | |
| "loss": 0.3677, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03696463479651679, | |
| "grad_norm": 1.8024444580078125, | |
| "learning_rate": 9.740174149534693e-05, | |
| "loss": 0.3316, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.039808068242402704, | |
| "grad_norm": 1.9301329851150513, | |
| "learning_rate": 9.686252995020249e-05, | |
| "loss": 0.3689, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04265150168828861, | |
| "grad_norm": 2.8067333698272705, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.3827, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04549493513417452, | |
| "grad_norm": 1.4591389894485474, | |
| "learning_rate": 9.563836295460398e-05, | |
| "loss": 0.3528, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04833836858006042, | |
| "grad_norm": 1.4871190786361694, | |
| "learning_rate": 9.495483482810688e-05, | |
| "loss": 0.3235, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05118180202594633, | |
| "grad_norm": 1.626112937927246, | |
| "learning_rate": 9.422472115147382e-05, | |
| "loss": 0.3317, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05402523547183224, | |
| "grad_norm": 1.4325222969055176, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.3437, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05686866891771814, | |
| "grad_norm": 2.8382790088653564, | |
| "learning_rate": 9.2628195591462e-05, | |
| "loss": 0.3757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05971210236360405, | |
| "grad_norm": 1.625089406967163, | |
| "learning_rate": 9.176364518546989e-05, | |
| "loss": 0.3304, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06255553580948996, | |
| "grad_norm": 1.772882342338562, | |
| "learning_rate": 9.08562300137157e-05, | |
| "loss": 0.3802, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06539896925537586, | |
| "grad_norm": 1.3592987060546875, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.3369, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06824240270126178, | |
| "grad_norm": 1.762557864189148, | |
| "learning_rate": 8.891708613973126e-05, | |
| "loss": 0.3376, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07108583614714768, | |
| "grad_norm": 1.9905650615692139, | |
| "learning_rate": 8.788761839251559e-05, | |
| "loss": 0.2961, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07108583614714768, | |
| "eval_loss": 0.3258455991744995, | |
| "eval_runtime": 4.0271, | |
| "eval_samples_per_second": 12.416, | |
| "eval_steps_per_second": 3.228, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07392926959303359, | |
| "grad_norm": 0.7239434719085693, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3381, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07677270303891949, | |
| "grad_norm": 0.8661226034164429, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.3448, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07961613648480541, | |
| "grad_norm": 1.6016333103179932, | |
| "learning_rate": 8.457416554680877e-05, | |
| "loss": 0.3474, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08245956993069131, | |
| "grad_norm": 1.2299487590789795, | |
| "learning_rate": 8.339895749467238e-05, | |
| "loss": 0.3493, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08530300337657722, | |
| "grad_norm": 1.4147472381591797, | |
| "learning_rate": 8.219063752844926e-05, | |
| "loss": 0.3162, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08814643682246312, | |
| "grad_norm": 1.3127275705337524, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.3306, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09098987026834904, | |
| "grad_norm": 1.7408323287963867, | |
| "learning_rate": 7.968033420621935e-05, | |
| "loss": 0.3163, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09383330371423494, | |
| "grad_norm": 1.461795687675476, | |
| "learning_rate": 7.838127775159452e-05, | |
| "loss": 0.2727, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09667673716012085, | |
| "grad_norm": 1.4612610340118408, | |
| "learning_rate": 7.705495977301078e-05, | |
| "loss": 0.3574, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09952017060600675, | |
| "grad_norm": 1.4245153665542603, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.3115, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10236360405189265, | |
| "grad_norm": 1.1729720830917358, | |
| "learning_rate": 7.43267549363537e-05, | |
| "loss": 0.3435, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10520703749777857, | |
| "grad_norm": 0.9695225954055786, | |
| "learning_rate": 7.292804904308087e-05, | |
| "loss": 0.2869, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10805047094366448, | |
| "grad_norm": 0.7456521391868591, | |
| "learning_rate": 7.150843984658754e-05, | |
| "loss": 0.2947, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11089390438955038, | |
| "grad_norm": 0.8560568690299988, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.3231, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11373733783543628, | |
| "grad_norm": 0.9865386486053467, | |
| "learning_rate": 6.861315478964841e-05, | |
| "loss": 0.302, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1165807712813222, | |
| "grad_norm": 0.9534958004951477, | |
| "learning_rate": 6.714085470206609e-05, | |
| "loss": 0.3014, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1194242047272081, | |
| "grad_norm": 0.8210452198982239, | |
| "learning_rate": 6.56543989209901e-05, | |
| "loss": 0.2968, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.12226763817309401, | |
| "grad_norm": 1.0526001453399658, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.3187, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1251110716189799, | |
| "grad_norm": 1.1468490362167358, | |
| "learning_rate": 6.264596732629e-05, | |
| "loss": 0.2978, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12795450506486583, | |
| "grad_norm": 1.0789867639541626, | |
| "learning_rate": 6.112749920933111e-05, | |
| "loss": 0.2907, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13079793851075172, | |
| "grad_norm": 1.4448879957199097, | |
| "learning_rate": 5.960188670239154e-05, | |
| "loss": 0.3332, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13364137195663764, | |
| "grad_norm": 1.1925578117370605, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.2723, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.13648480540252356, | |
| "grad_norm": 1.3483730554580688, | |
| "learning_rate": 5.653634995836856e-05, | |
| "loss": 0.3051, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13932823884840945, | |
| "grad_norm": 1.0803078413009644, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.2854, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14217167229429536, | |
| "grad_norm": 1.0243525505065918, | |
| "learning_rate": 5.346365004163145e-05, | |
| "loss": 0.2797, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14217167229429536, | |
| "eval_loss": 0.27564024925231934, | |
| "eval_runtime": 4.0615, | |
| "eval_samples_per_second": 12.311, | |
| "eval_steps_per_second": 3.201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14501510574018128, | |
| "grad_norm": 1.0136526823043823, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.3151, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.14785853918606717, | |
| "grad_norm": 1.1708089113235474, | |
| "learning_rate": 5.0398113297608465e-05, | |
| "loss": 0.2924, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1507019726319531, | |
| "grad_norm": 0.8153492212295532, | |
| "learning_rate": 4.887250079066892e-05, | |
| "loss": 0.2776, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.15354540607783898, | |
| "grad_norm": 1.1344809532165527, | |
| "learning_rate": 4.7354032673710005e-05, | |
| "loss": 0.2746, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1563888395237249, | |
| "grad_norm": 1.1401007175445557, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.309, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15923227296961082, | |
| "grad_norm": 1.3479905128479004, | |
| "learning_rate": 4.43456010790099e-05, | |
| "loss": 0.2876, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1620757064154967, | |
| "grad_norm": 1.0521594285964966, | |
| "learning_rate": 4.285914529793391e-05, | |
| "loss": 0.2562, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.16491913986138262, | |
| "grad_norm": 0.9862216711044312, | |
| "learning_rate": 4.13868452103516e-05, | |
| "loss": 0.2832, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.16776257330726851, | |
| "grad_norm": 1.2180746793746948, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.3047, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.17060600675315443, | |
| "grad_norm": 1.5846315622329712, | |
| "learning_rate": 3.8491560153412466e-05, | |
| "loss": 0.2768, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17344944019904035, | |
| "grad_norm": 1.3017767667770386, | |
| "learning_rate": 3.707195095691913e-05, | |
| "loss": 0.2877, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.17629287364492624, | |
| "grad_norm": 1.473238468170166, | |
| "learning_rate": 3.567324506364632e-05, | |
| "loss": 0.2664, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.17913630709081216, | |
| "grad_norm": 1.2154439687728882, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.2768, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.18197974053669808, | |
| "grad_norm": 1.683435082435608, | |
| "learning_rate": 3.2945040226989244e-05, | |
| "loss": 0.2896, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.18482317398258397, | |
| "grad_norm": 1.3778927326202393, | |
| "learning_rate": 3.16187222484055e-05, | |
| "loss": 0.295, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.18766660742846988, | |
| "grad_norm": 1.4608365297317505, | |
| "learning_rate": 3.0319665793780648e-05, | |
| "loss": 0.2611, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.19051004087435577, | |
| "grad_norm": 1.2854911088943481, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.2541, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.1933534743202417, | |
| "grad_norm": 1.3991892337799072, | |
| "learning_rate": 2.7809362471550748e-05, | |
| "loss": 0.2624, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1961969077661276, | |
| "grad_norm": 1.1210330724716187, | |
| "learning_rate": 2.660104250532764e-05, | |
| "loss": 0.2684, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1990403412120135, | |
| "grad_norm": 1.145573616027832, | |
| "learning_rate": 2.5425834453191232e-05, | |
| "loss": 0.2504, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.20188377465789942, | |
| "grad_norm": 0.9745646715164185, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.249, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2047272081037853, | |
| "grad_norm": 1.0583624839782715, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.2482, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.20757064154967123, | |
| "grad_norm": 1.106729507446289, | |
| "learning_rate": 2.2112381607484417e-05, | |
| "loss": 0.2899, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.21041407499555714, | |
| "grad_norm": 1.0823482275009155, | |
| "learning_rate": 2.1082913860268765e-05, | |
| "loss": 0.2543, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.21325750844144303, | |
| "grad_norm": 0.9167066216468811, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.2498, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.21325750844144303, | |
| "eval_loss": 0.26534104347229004, | |
| "eval_runtime": 4.0551, | |
| "eval_samples_per_second": 12.33, | |
| "eval_steps_per_second": 3.206, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.21610094188732895, | |
| "grad_norm": 1.3717762231826782, | |
| "learning_rate": 1.91437699862843e-05, | |
| "loss": 0.2886, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.21894437533321487, | |
| "grad_norm": 1.5089960098266602, | |
| "learning_rate": 1.8236354814530112e-05, | |
| "loss": 0.3046, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.22178780877910076, | |
| "grad_norm": 1.2876425981521606, | |
| "learning_rate": 1.7371804408538024e-05, | |
| "loss": 0.2682, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.22463124222498668, | |
| "grad_norm": 1.4826658964157104, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.2612, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.22747467567087257, | |
| "grad_norm": 1.2903155088424683, | |
| "learning_rate": 1.577527884852619e-05, | |
| "loss": 0.2599, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23031810911675848, | |
| "grad_norm": 1.2806668281555176, | |
| "learning_rate": 1.5045165171893116e-05, | |
| "loss": 0.2419, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2331615425626444, | |
| "grad_norm": 1.1345335245132446, | |
| "learning_rate": 1.4361637045396029e-05, | |
| "loss": 0.2579, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2360049760085303, | |
| "grad_norm": 1.1329256296157837, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.2659, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.2388484094544162, | |
| "grad_norm": 1.2562272548675537, | |
| "learning_rate": 1.313747004979751e-05, | |
| "loss": 0.2676, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.24169184290030213, | |
| "grad_norm": 0.992720901966095, | |
| "learning_rate": 1.2598258504653081e-05, | |
| "loss": 0.2283, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.24453527634618802, | |
| "grad_norm": 1.2588672637939453, | |
| "learning_rate": 1.2108485493362765e-05, | |
| "loss": 0.2456, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.24737870979207394, | |
| "grad_norm": 0.9704244136810303, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.2605, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2502221432379598, | |
| "grad_norm": 0.993431031703949, | |
| "learning_rate": 1.1279480977092635e-05, | |
| "loss": 0.2861, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2530655766838457, | |
| "grad_norm": 1.2297654151916504, | |
| "learning_rate": 1.094121605429547e-05, | |
| "loss": 0.2832, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.25590901012973166, | |
| "grad_norm": 1.498766303062439, | |
| "learning_rate": 1.0654321702726141e-05, | |
| "loss": 0.271, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25875244357561755, | |
| "grad_norm": 1.326579213142395, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.2704, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.26159587702150344, | |
| "grad_norm": 1.417798399925232, | |
| "learning_rate": 1.0235922451385733e-05, | |
| "loss": 0.2509, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2644393104673894, | |
| "grad_norm": 1.0304580926895142, | |
| "learning_rate": 1.0104905386425733e-05, | |
| "loss": 0.2516, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.2672827439132753, | |
| "grad_norm": 1.153357982635498, | |
| "learning_rate": 1.002623399352217e-05, | |
| "loss": 0.2606, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.27012617735916117, | |
| "grad_norm": 1.3540794849395752, | |
| "learning_rate": 1e-05, | |
| "loss": 0.267, | |
| "step": 95 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 95, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.173151075448914e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |