| { | |
| "best_metric": 0.15225209295749664, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.17006802721088435, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017006802721088435, | |
| "grad_norm": 0.5296435952186584, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1901, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017006802721088435, | |
| "eval_loss": 0.5936321020126343, | |
| "eval_runtime": 99.2183, | |
| "eval_samples_per_second": 9.978, | |
| "eval_steps_per_second": 2.5, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003401360544217687, | |
| "grad_norm": 0.46403637528419495, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1959, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00510204081632653, | |
| "grad_norm": 0.5744128823280334, | |
| "learning_rate": 3e-05, | |
| "loss": 0.2195, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006802721088435374, | |
| "grad_norm": 0.5589671730995178, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2317, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008503401360544218, | |
| "grad_norm": 0.5408557653427124, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2098, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01020408163265306, | |
| "grad_norm": 0.514587938785553, | |
| "learning_rate": 6e-05, | |
| "loss": 0.2101, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011904761904761904, | |
| "grad_norm": 0.46519431471824646, | |
| "learning_rate": 7e-05, | |
| "loss": 0.1949, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013605442176870748, | |
| "grad_norm": 0.48039916157722473, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2285, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015306122448979591, | |
| "grad_norm": 0.3992774188518524, | |
| "learning_rate": 9e-05, | |
| "loss": 0.1829, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017006802721088437, | |
| "grad_norm": 0.37706080079078674, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1575, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01870748299319728, | |
| "grad_norm": 0.33965542912483215, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.184, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 0.3842385709285736, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.1588, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.022108843537414966, | |
| "grad_norm": 0.5256059169769287, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.2427, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023809523809523808, | |
| "grad_norm": 0.5123369693756104, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.1808, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025510204081632654, | |
| "grad_norm": 0.42671579122543335, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.1534, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.027210884353741496, | |
| "grad_norm": 0.362161785364151, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.1293, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02891156462585034, | |
| "grad_norm": 0.4058263301849365, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.1596, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030612244897959183, | |
| "grad_norm": 0.36066436767578125, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.1386, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03231292517006803, | |
| "grad_norm": 0.34079501032829285, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.1577, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.034013605442176874, | |
| "grad_norm": 0.34605899453163147, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.1488, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 0.29584625363349915, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.1254, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03741496598639456, | |
| "grad_norm": 0.3019483983516693, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.1597, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0391156462585034, | |
| "grad_norm": 0.347933828830719, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.1477, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 0.35964134335517883, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.162, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04251700680272109, | |
| "grad_norm": 0.3269605338573456, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.1221, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04421768707482993, | |
| "grad_norm": 0.39577123522758484, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.16, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04591836734693878, | |
| "grad_norm": 1.1477911472320557, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.2382, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.047619047619047616, | |
| "grad_norm": 0.40509581565856934, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.1499, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04931972789115646, | |
| "grad_norm": 0.3921804428100586, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.1597, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05102040816326531, | |
| "grad_norm": 0.3694240152835846, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.1531, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05272108843537415, | |
| "grad_norm": 0.48857390880584717, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.1802, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05442176870748299, | |
| "grad_norm": 0.518921434879303, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.2015, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05612244897959184, | |
| "grad_norm": 0.45379164814949036, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.1666, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05782312925170068, | |
| "grad_norm": 0.6328680515289307, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.314, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05952380952380952, | |
| "grad_norm": 0.41080063581466675, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.1411, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 0.47048354148864746, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.1458, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06292517006802721, | |
| "grad_norm": 0.4776947796344757, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.2109, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06462585034013606, | |
| "grad_norm": 0.5354244709014893, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.1569, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0663265306122449, | |
| "grad_norm": 0.4933754801750183, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.1632, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06802721088435375, | |
| "grad_norm": 0.526614248752594, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.2226, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06972789115646258, | |
| "grad_norm": 0.6038437485694885, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.2194, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 0.5840771198272705, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.2245, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07312925170068027, | |
| "grad_norm": 0.5161733031272888, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.1846, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07482993197278912, | |
| "grad_norm": 0.5809618830680847, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.2079, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07653061224489796, | |
| "grad_norm": 0.5962471961975098, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.2366, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0782312925170068, | |
| "grad_norm": 0.6618085503578186, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.2596, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07993197278911565, | |
| "grad_norm": 0.5380584597587585, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.2301, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.631349503993988, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.2292, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 1.3007142543792725, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.2722, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08503401360544217, | |
| "grad_norm": 2.0485315322875977, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.3315, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08503401360544217, | |
| "eval_loss": 0.17823144793510437, | |
| "eval_runtime": 100.0032, | |
| "eval_samples_per_second": 9.9, | |
| "eval_steps_per_second": 2.48, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08673469387755102, | |
| "grad_norm": 0.2999962270259857, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 0.1368, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08843537414965986, | |
| "grad_norm": 0.30443039536476135, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 0.0848, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.09013605442176871, | |
| "grad_norm": 0.25375548005104065, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 0.1295, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.09183673469387756, | |
| "grad_norm": 0.17752642929553986, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 0.0672, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0935374149659864, | |
| "grad_norm": 0.18084105849266052, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.1213, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 0.26786619424819946, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 0.1161, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.09693877551020408, | |
| "grad_norm": 0.22582994401454926, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 0.1128, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09863945578231292, | |
| "grad_norm": 0.2891770899295807, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 0.139, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.10034013605442177, | |
| "grad_norm": 0.2367025464773178, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 0.1246, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 0.18042106926441193, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.1039, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10374149659863946, | |
| "grad_norm": 0.19133102893829346, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 0.1255, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1054421768707483, | |
| "grad_norm": 0.2340659350156784, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 0.1529, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 0.2856714725494385, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 0.1337, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.10884353741496598, | |
| "grad_norm": 0.24162790179252625, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 0.119, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.11054421768707483, | |
| "grad_norm": 0.19808998703956604, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.1318, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11224489795918367, | |
| "grad_norm": 0.2100956290960312, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.1239, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.11394557823129252, | |
| "grad_norm": 0.20403148233890533, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.1008, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.11564625850340136, | |
| "grad_norm": 0.2087327241897583, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 0.1288, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.11734693877551021, | |
| "grad_norm": 0.20853887498378754, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 0.1189, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.11904761904761904, | |
| "grad_norm": 0.261677086353302, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.1297, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12074829931972789, | |
| "grad_norm": 0.25025635957717896, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 0.1426, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 0.2275075763463974, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.1177, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.12414965986394558, | |
| "grad_norm": 0.19386127591133118, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 0.1212, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.12585034013605442, | |
| "grad_norm": 0.2676469683647156, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.1361, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.12755102040816327, | |
| "grad_norm": 0.4179306924343109, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.1405, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1292517006802721, | |
| "grad_norm": 0.285391241312027, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 0.1426, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.13095238095238096, | |
| "grad_norm": 0.37067097425460815, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 0.125, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.1326530612244898, | |
| "grad_norm": 0.27059873938560486, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 0.1446, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.13435374149659865, | |
| "grad_norm": 0.32261890172958374, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 0.1377, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.1360544217687075, | |
| "grad_norm": 0.4681248068809509, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.2576, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1377551020408163, | |
| "grad_norm": 0.39090844988822937, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 0.2131, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.13945578231292516, | |
| "grad_norm": 0.2745368778705597, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.1218, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.141156462585034, | |
| "grad_norm": 0.4222804009914398, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 0.2313, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.26606062054634094, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.1231, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1445578231292517, | |
| "grad_norm": 0.39861971139907837, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.1935, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.14625850340136054, | |
| "grad_norm": 0.34635743498802185, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.1142, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.14795918367346939, | |
| "grad_norm": 0.4157678186893463, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 0.188, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.14965986394557823, | |
| "grad_norm": 0.3788713216781616, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.1562, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.15136054421768708, | |
| "grad_norm": 0.3447698950767517, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 0.1649, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.15306122448979592, | |
| "grad_norm": 0.40397417545318604, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.1885, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15476190476190477, | |
| "grad_norm": 0.44152534008026123, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 0.2558, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.1564625850340136, | |
| "grad_norm": 0.35763365030288696, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.1404, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.15816326530612246, | |
| "grad_norm": 0.39760518074035645, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 0.1549, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1598639455782313, | |
| "grad_norm": 0.5707307457923889, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.3187, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.16156462585034015, | |
| "grad_norm": 0.5781694054603577, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.208, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.44152382016181946, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.174, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.1649659863945578, | |
| "grad_norm": 0.5395876169204712, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 0.1957, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.6618689894676208, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 0.2403, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1683673469387755, | |
| "grad_norm": 0.7297075390815735, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 0.2676, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "grad_norm": 1.3715710639953613, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.2514, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17006802721088435, | |
| "eval_loss": 0.15225209295749664, | |
| "eval_runtime": 100.0235, | |
| "eval_samples_per_second": 9.898, | |
| "eval_steps_per_second": 2.479, | |
| "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": 1.84380938187178e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |