| { | |
| "best_metric": 4.617598533630371, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-200", | |
| "epoch": 0.33927056827820185, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016963528413910093, | |
| "grad_norm": 0.22393453121185303, | |
| "learning_rate": 1e-05, | |
| "loss": 5.4505, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016963528413910093, | |
| "eval_loss": 5.438750743865967, | |
| "eval_runtime": 56.252, | |
| "eval_samples_per_second": 17.653, | |
| "eval_steps_per_second": 4.427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033927056827820186, | |
| "grad_norm": 0.2217618077993393, | |
| "learning_rate": 2e-05, | |
| "loss": 5.4465, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005089058524173028, | |
| "grad_norm": 0.21864764392375946, | |
| "learning_rate": 3e-05, | |
| "loss": 5.4671, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006785411365564037, | |
| "grad_norm": 0.2050054371356964, | |
| "learning_rate": 4e-05, | |
| "loss": 5.4368, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008481764206955046, | |
| "grad_norm": 0.196041539311409, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4142, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010178117048346057, | |
| "grad_norm": 0.165675550699234, | |
| "learning_rate": 6e-05, | |
| "loss": 5.411, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011874469889737066, | |
| "grad_norm": 0.1644248366355896, | |
| "learning_rate": 7e-05, | |
| "loss": 5.39, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013570822731128074, | |
| "grad_norm": 0.2563374638557434, | |
| "learning_rate": 8e-05, | |
| "loss": 5.385, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "grad_norm": 0.22238920629024506, | |
| "learning_rate": 9e-05, | |
| "loss": 5.3554, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016963528413910092, | |
| "grad_norm": 0.17928071320056915, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3673, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018659881255301103, | |
| "grad_norm": 0.19560983777046204, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 5.3341, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": 0.18393296003341675, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 5.3354, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02205258693808312, | |
| "grad_norm": 0.1497751772403717, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 5.3168, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02374893977947413, | |
| "grad_norm": 0.14602182805538177, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 5.3135, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02544529262086514, | |
| "grad_norm": 0.14209671318531036, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 5.2933, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02714164546225615, | |
| "grad_norm": 0.14373886585235596, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 5.2735, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02883799830364716, | |
| "grad_norm": 0.1724289208650589, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 5.2908, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "grad_norm": 0.1537420004606247, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 5.2615, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.032230703986429174, | |
| "grad_norm": 0.1800667643547058, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 5.2765, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.033927056827820185, | |
| "grad_norm": 0.13769733905792236, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 5.2708, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.035623409669211195, | |
| "grad_norm": 0.13515126705169678, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 5.2651, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.037319762510602206, | |
| "grad_norm": 0.14688712358474731, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 5.2578, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.039016115351993216, | |
| "grad_norm": 0.13153477013111115, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 5.242, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04071246819338423, | |
| "grad_norm": 0.18640489876270294, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 5.2384, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04240882103477523, | |
| "grad_norm": 0.15873999893665314, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 5.2195, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04410517387616624, | |
| "grad_norm": 0.1275458186864853, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 5.2216, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04580152671755725, | |
| "grad_norm": 0.1359083205461502, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 5.2216, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04749787955894826, | |
| "grad_norm": 0.20529517531394958, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 5.2159, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04919423240033927, | |
| "grad_norm": 0.1422276496887207, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 5.2329, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05089058524173028, | |
| "grad_norm": 0.1549217402935028, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 5.2205, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05258693808312129, | |
| "grad_norm": 0.1429785192012787, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 5.2283, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0542832909245123, | |
| "grad_norm": 0.16987676918506622, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 5.2151, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05597964376590331, | |
| "grad_norm": 0.17089951038360596, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 5.2081, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05767599660729432, | |
| "grad_norm": 0.14339880645275116, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 5.1844, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05937234944868533, | |
| "grad_norm": 0.15484975278377533, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 5.2106, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.061068702290076333, | |
| "grad_norm": 0.1805362105369568, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 5.1704, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06276505513146735, | |
| "grad_norm": 0.24406695365905762, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 5.1808, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06446140797285835, | |
| "grad_norm": 0.2286711484193802, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 5.2008, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06615776081424936, | |
| "grad_norm": 0.1707409918308258, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 5.1684, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06785411365564037, | |
| "grad_norm": 0.23671557009220123, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 5.1728, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06955046649703138, | |
| "grad_norm": 0.2255028337240219, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 5.1687, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07124681933842239, | |
| "grad_norm": 0.20494744181632996, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 5.1527, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0729431721798134, | |
| "grad_norm": 0.2836698293685913, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 5.1501, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07463952502120441, | |
| "grad_norm": 0.2934689521789551, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 5.1391, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07633587786259542, | |
| "grad_norm": 0.2627279758453369, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 5.1452, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07803223070398643, | |
| "grad_norm": 0.3738890588283539, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 5.1383, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07972858354537744, | |
| "grad_norm": 0.5340456366539001, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 5.1033, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08142493638676845, | |
| "grad_norm": 0.6249650120735168, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.1319, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08312128922815945, | |
| "grad_norm": 0.30934613943099976, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 5.1361, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08481764206955046, | |
| "grad_norm": 0.4844401180744171, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 5.1821, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08481764206955046, | |
| "eval_loss": 5.097905158996582, | |
| "eval_runtime": 56.5855, | |
| "eval_samples_per_second": 17.549, | |
| "eval_steps_per_second": 4.4, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08651399491094147, | |
| "grad_norm": 0.4664671719074249, | |
| "learning_rate": 8.894386393810563e-05, | |
| "loss": 5.0947, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08821034775233248, | |
| "grad_norm": 0.5651379227638245, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 5.0961, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0899067005937235, | |
| "grad_norm": 0.4858242869377136, | |
| "learning_rate": 8.788574348801675e-05, | |
| "loss": 5.0864, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0916030534351145, | |
| "grad_norm": 0.354536235332489, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 5.0991, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09329940627650551, | |
| "grad_norm": 0.49886053800582886, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 5.0911, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09499575911789652, | |
| "grad_norm": 0.28070664405822754, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 5.0681, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.09669211195928754, | |
| "grad_norm": 0.485439658164978, | |
| "learning_rate": 8.564642241456986e-05, | |
| "loss": 5.0443, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09838846480067855, | |
| "grad_norm": 0.30182307958602905, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 5.0502, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.10008481764206956, | |
| "grad_norm": 0.40525439381599426, | |
| "learning_rate": 8.44676704559283e-05, | |
| "loss": 5.0333, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.10178117048346055, | |
| "grad_norm": 0.3293815553188324, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 4.9967, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10347752332485156, | |
| "grad_norm": 0.33745312690734863, | |
| "learning_rate": 8.32512286056924e-05, | |
| "loss": 5.0233, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.10517387616624257, | |
| "grad_norm": 0.3826795220375061, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 5.0087, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.10687022900763359, | |
| "grad_norm": 0.3098697066307068, | |
| "learning_rate": 8.199842702516583e-05, | |
| "loss": 5.0125, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1085665818490246, | |
| "grad_norm": 0.4641379714012146, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 4.9795, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1102629346904156, | |
| "grad_norm": 0.47782716155052185, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 4.9579, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11195928753180662, | |
| "grad_norm": 0.32422932982444763, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 4.9768, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.11365564037319763, | |
| "grad_norm": 0.3210996389389038, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 4.9692, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.11535199321458864, | |
| "grad_norm": 0.45930537581443787, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 4.9654, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.11704834605597965, | |
| "grad_norm": 0.6370431184768677, | |
| "learning_rate": 7.803575286758364e-05, | |
| "loss": 4.9298, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.11874469889737066, | |
| "grad_norm": 0.5103404521942139, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 4.9354, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12044105173876166, | |
| "grad_norm": 0.565083920955658, | |
| "learning_rate": 7.66515864363997e-05, | |
| "loss": 4.9274, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.12213740458015267, | |
| "grad_norm": 1.2758535146713257, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 4.9427, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.12383375742154368, | |
| "grad_norm": 1.1843165159225464, | |
| "learning_rate": 7.52382768867422e-05, | |
| "loss": 4.9209, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1255301102629347, | |
| "grad_norm": 0.7486790418624878, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 4.8977, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1272264631043257, | |
| "grad_norm": 0.6123133301734924, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 4.8696, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1289228159457167, | |
| "grad_norm": 0.5507182478904724, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 4.8805, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.13061916878710772, | |
| "grad_norm": 0.9851804971694946, | |
| "learning_rate": 7.233044034264034e-05, | |
| "loss": 4.8914, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.13231552162849872, | |
| "grad_norm": 1.4381717443466187, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 4.8671, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.13401187446988974, | |
| "grad_norm": 0.681228756904602, | |
| "learning_rate": 7.083909302476453e-05, | |
| "loss": 4.8699, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.13570822731128074, | |
| "grad_norm": 0.987644374370575, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 4.8247, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13740458015267176, | |
| "grad_norm": 1.7508363723754883, | |
| "learning_rate": 6.932495846462261e-05, | |
| "loss": 4.8497, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.13910093299406276, | |
| "grad_norm": 0.7650771737098694, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 4.8359, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.14079728583545378, | |
| "grad_norm": 2.110387086868286, | |
| "learning_rate": 6.778969234612584e-05, | |
| "loss": 4.8392, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.14249363867684478, | |
| "grad_norm": 1.4256200790405273, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 4.8331, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.1441899915182358, | |
| "grad_norm": 2.090686082839966, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 4.8373, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1458863443596268, | |
| "grad_norm": 1.60507333278656, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.8399, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.1475826972010178, | |
| "grad_norm": 1.4971212148666382, | |
| "learning_rate": 6.466250186922325e-05, | |
| "loss": 4.8236, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.14927905004240882, | |
| "grad_norm": 1.3327971696853638, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 4.7833, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.15097540288379982, | |
| "grad_norm": 2.142843008041382, | |
| "learning_rate": 6.307399704769099e-05, | |
| "loss": 4.8183, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.15267175572519084, | |
| "grad_norm": 1.617634892463684, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 4.8085, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15436810856658184, | |
| "grad_norm": 0.9406760334968567, | |
| "learning_rate": 6.147119600233758e-05, | |
| "loss": 4.7993, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.15606446140797287, | |
| "grad_norm": 1.0688856840133667, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 4.7958, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.15776081424936386, | |
| "grad_norm": 0.9656695127487183, | |
| "learning_rate": 5.985585137257401e-05, | |
| "loss": 4.7795, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.1594571670907549, | |
| "grad_norm": 0.9346708059310913, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 4.7689, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.16115351993214588, | |
| "grad_norm": 1.5974655151367188, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 4.767, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1628498727735369, | |
| "grad_norm": 0.7257375717163086, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 4.747, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.1645462256149279, | |
| "grad_norm": 1.88131582736969, | |
| "learning_rate": 5.6594608567103456e-05, | |
| "loss": 4.7824, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.1662425784563189, | |
| "grad_norm": 1.3980379104614258, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 4.7555, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.16793893129770993, | |
| "grad_norm": 2.1029675006866455, | |
| "learning_rate": 5.495227651252315e-05, | |
| "loss": 4.7622, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.16963528413910092, | |
| "grad_norm": 1.9871934652328491, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 4.7454, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16963528413910092, | |
| "eval_loss": 4.748427391052246, | |
| "eval_runtime": 56.6126, | |
| "eval_samples_per_second": 17.54, | |
| "eval_steps_per_second": 4.398, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17133163698049195, | |
| "grad_norm": 0.9891380071640015, | |
| "learning_rate": 5.330452921628497e-05, | |
| "loss": 4.7747, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.17302798982188294, | |
| "grad_norm": 0.9591396450996399, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 4.7587, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.17472434266327397, | |
| "grad_norm": 1.0332738161087036, | |
| "learning_rate": 5.165316846586541e-05, | |
| "loss": 4.7587, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.17642069550466496, | |
| "grad_norm": 0.5275875329971313, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 4.746, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.178117048346056, | |
| "grad_norm": 0.9619452357292175, | |
| "learning_rate": 5e-05, | |
| "loss": 4.7587, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.179813401187447, | |
| "grad_norm": 0.7576751112937927, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 4.7554, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.181509754028838, | |
| "grad_norm": 0.6569339632987976, | |
| "learning_rate": 4.834683153413459e-05, | |
| "loss": 4.7335, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.183206106870229, | |
| "grad_norm": 0.6780545115470886, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 4.7189, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.18490245971162, | |
| "grad_norm": 0.48617953062057495, | |
| "learning_rate": 4.669547078371504e-05, | |
| "loss": 4.7245, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.18659881255301103, | |
| "grad_norm": 0.6515666842460632, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 4.7163, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18829516539440203, | |
| "grad_norm": 0.5565833449363708, | |
| "learning_rate": 4.504772348747687e-05, | |
| "loss": 4.7028, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.18999151823579305, | |
| "grad_norm": 0.8027333617210388, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 4.704, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.19168787107718405, | |
| "grad_norm": 0.8671331405639648, | |
| "learning_rate": 4.3405391432896555e-05, | |
| "loss": 4.7126, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.19338422391857507, | |
| "grad_norm": 0.42321425676345825, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 4.7095, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.19508057675996607, | |
| "grad_norm": 1.3536083698272705, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 4.705, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.1967769296013571, | |
| "grad_norm": 1.1061015129089355, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 4.7055, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.1984732824427481, | |
| "grad_norm": 0.7384159564971924, | |
| "learning_rate": 4.0144148627425993e-05, | |
| "loss": 4.6756, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.2001696352841391, | |
| "grad_norm": 0.6042837500572205, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 4.6905, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.2018659881255301, | |
| "grad_norm": 0.4404369294643402, | |
| "learning_rate": 3.852880399766243e-05, | |
| "loss": 4.657, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.2035623409669211, | |
| "grad_norm": 0.457706093788147, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 4.6612, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.20525869380831213, | |
| "grad_norm": 0.5727593302726746, | |
| "learning_rate": 3.6926002952309016e-05, | |
| "loss": 4.6873, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.20695504664970313, | |
| "grad_norm": 1.052722692489624, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 4.6869, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.20865139949109415, | |
| "grad_norm": 1.327793002128601, | |
| "learning_rate": 3.533749813077677e-05, | |
| "loss": 4.6816, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.21034775233248515, | |
| "grad_norm": 0.7162137627601624, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.6593, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.21204410517387617, | |
| "grad_norm": 0.6135863065719604, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 4.6651, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.21374045801526717, | |
| "grad_norm": 0.411624014377594, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 4.6851, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.2154368108566582, | |
| "grad_norm": 0.5264264941215515, | |
| "learning_rate": 3.221030765387417e-05, | |
| "loss": 4.6623, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.2171331636980492, | |
| "grad_norm": 0.3675892949104309, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 4.6463, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.21882951653944022, | |
| "grad_norm": 0.553791344165802, | |
| "learning_rate": 3.0675041535377405e-05, | |
| "loss": 4.65, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.2205258693808312, | |
| "grad_norm": 0.537880003452301, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 4.6576, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.4886820912361145, | |
| "learning_rate": 2.916090697523549e-05, | |
| "loss": 4.642, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.22391857506361323, | |
| "grad_norm": 1.0316487550735474, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 4.6572, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.22561492790500423, | |
| "grad_norm": 1.0013306140899658, | |
| "learning_rate": 2.766955965735968e-05, | |
| "loss": 4.6746, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.22731128074639526, | |
| "grad_norm": 0.5017285943031311, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 4.66, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.22900763358778625, | |
| "grad_norm": 0.45447802543640137, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 4.659, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.23070398642917728, | |
| "grad_norm": 0.7801204323768616, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 4.6517, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.23240033927056827, | |
| "grad_norm": 0.9556665420532227, | |
| "learning_rate": 2.476172311325783e-05, | |
| "loss": 4.6501, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.2340966921119593, | |
| "grad_norm": 0.5217021107673645, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 4.6475, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.2357930449533503, | |
| "grad_norm": 0.867202877998352, | |
| "learning_rate": 2.3348413563600325e-05, | |
| "loss": 4.6667, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.23748939779474132, | |
| "grad_norm": 1.1739754676818848, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 4.6358, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23918575063613232, | |
| "grad_norm": 0.5438863635063171, | |
| "learning_rate": 2.196424713241637e-05, | |
| "loss": 4.6374, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.2408821034775233, | |
| "grad_norm": 1.2138160467147827, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 4.6412, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.24257845631891434, | |
| "grad_norm": 0.36607611179351807, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 4.6558, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.24427480916030533, | |
| "grad_norm": 0.7016098499298096, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 4.6366, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.24597116200169636, | |
| "grad_norm": 0.448512464761734, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 4.6299, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.24766751484308736, | |
| "grad_norm": 0.5045221447944641, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 4.6381, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.24936386768447838, | |
| "grad_norm": 0.36250588297843933, | |
| "learning_rate": 1.800157297483417e-05, | |
| "loss": 4.6246, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.2510602205258694, | |
| "grad_norm": 0.39792773127555847, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 4.6358, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.2527565733672604, | |
| "grad_norm": 0.5288111567497253, | |
| "learning_rate": 1.6748771394307585e-05, | |
| "loss": 4.6276, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.2544529262086514, | |
| "grad_norm": 0.4160231649875641, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 4.6336, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2544529262086514, | |
| "eval_loss": 4.633537292480469, | |
| "eval_runtime": 56.6129, | |
| "eval_samples_per_second": 17.54, | |
| "eval_steps_per_second": 4.398, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.2561492790500424, | |
| "grad_norm": 1.838320016860962, | |
| "learning_rate": 1.553232954407171e-05, | |
| "loss": 4.6318, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.2578456318914334, | |
| "grad_norm": 0.8034282922744751, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 4.6341, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.2595419847328244, | |
| "grad_norm": 1.3815810680389404, | |
| "learning_rate": 1.435357758543015e-05, | |
| "loss": 4.6232, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.26123833757421544, | |
| "grad_norm": 0.47848081588745117, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 4.6616, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.26293469041560646, | |
| "grad_norm": 0.8518421053886414, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 4.6559, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.26463104325699743, | |
| "grad_norm": 0.40979698300361633, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 4.6467, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.26632739609838846, | |
| "grad_norm": 1.3941459655761719, | |
| "learning_rate": 1.2114256511983274e-05, | |
| "loss": 4.6397, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.2680237489397795, | |
| "grad_norm": 0.5115864276885986, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 4.6474, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.2697201017811705, | |
| "grad_norm": 0.9543215036392212, | |
| "learning_rate": 1.1056136061894384e-05, | |
| "loss": 4.6365, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.2714164546225615, | |
| "grad_norm": 0.6574369072914124, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 4.628, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2731128074639525, | |
| "grad_norm": 0.55491703748703, | |
| "learning_rate": 1.0040600155253765e-05, | |
| "loss": 4.6502, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.2748091603053435, | |
| "grad_norm": 1.3687418699264526, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 4.6242, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.2765055131467345, | |
| "grad_norm": 0.45188108086586, | |
| "learning_rate": 9.068759265665384e-06, | |
| "loss": 4.6223, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.2782018659881255, | |
| "grad_norm": 1.3373568058013916, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 4.6199, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.27989821882951654, | |
| "grad_norm": 1.3738486766815186, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 4.6138, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.28159457167090757, | |
| "grad_norm": 0.3830588459968567, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 4.6271, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.28329092451229854, | |
| "grad_norm": 1.2534278631210327, | |
| "learning_rate": 7.260364370723044e-06, | |
| "loss": 4.6273, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.28498727735368956, | |
| "grad_norm": 1.1280326843261719, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 4.6316, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.2866836301950806, | |
| "grad_norm": 0.4303630292415619, | |
| "learning_rate": 6.425787818636131e-06, | |
| "loss": 4.6278, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.2883799830364716, | |
| "grad_norm": 0.6808664202690125, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 4.6001, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2900763358778626, | |
| "grad_norm": 1.4083077907562256, | |
| "learning_rate": 5.6388590278194096e-06, | |
| "loss": 4.6067, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.2917726887192536, | |
| "grad_norm": 0.7814533114433289, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 4.6199, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.29346904156064463, | |
| "grad_norm": 0.3594047427177429, | |
| "learning_rate": 4.900438493352055e-06, | |
| "loss": 4.6152, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.2951653944020356, | |
| "grad_norm": 0.7063488960266113, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 4.6242, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.2968617472434266, | |
| "grad_norm": 0.9455859661102295, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 4.6253, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.29855810008481765, | |
| "grad_norm": 0.6382616758346558, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 4.625, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.30025445292620867, | |
| "grad_norm": 0.3721851408481598, | |
| "learning_rate": 3.5722980755146517e-06, | |
| "loss": 4.6252, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.30195080576759964, | |
| "grad_norm": 0.9982456564903259, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 4.6127, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.30364715860899066, | |
| "grad_norm": 1.02492094039917, | |
| "learning_rate": 2.9840304941919415e-06, | |
| "loss": 4.6248, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.3053435114503817, | |
| "grad_norm": 0.37319836020469666, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 4.6097, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3070398642917727, | |
| "grad_norm": 0.36814001202583313, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 4.6083, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.3087362171331637, | |
| "grad_norm": 0.6440801620483398, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 4.6057, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.3104325699745547, | |
| "grad_norm": 0.7002668380737305, | |
| "learning_rate": 1.962316193157593e-06, | |
| "loss": 4.6293, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.31212892281594573, | |
| "grad_norm": 0.7051588296890259, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 4.6247, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.3138252756573367, | |
| "grad_norm": 0.6539353132247925, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 4.6166, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.3155216284987277, | |
| "grad_norm": 0.3288273215293884, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 4.59, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.31721798134011875, | |
| "grad_norm": 0.4478888213634491, | |
| "learning_rate": 1.1506584608200367e-06, | |
| "loss": 4.6333, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.3189143341815098, | |
| "grad_norm": 0.5312961935997009, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 4.6403, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.32061068702290074, | |
| "grad_norm": 0.5868805050849915, | |
| "learning_rate": 8.247462563808817e-07, | |
| "loss": 4.6435, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.32230703986429177, | |
| "grad_norm": 0.4826406240463257, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 4.6201, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3240033927056828, | |
| "grad_norm": 0.49794068932533264, | |
| "learning_rate": 5.526064699265753e-07, | |
| "loss": 4.6, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.3256997455470738, | |
| "grad_norm": 0.33173584938049316, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 4.6134, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.3273960983884648, | |
| "grad_norm": 0.4233497083187103, | |
| "learning_rate": 3.3453668231809286e-07, | |
| "loss": 4.6347, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.3290924512298558, | |
| "grad_norm": 0.321246474981308, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 4.6307, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.33078880407124683, | |
| "grad_norm": 0.33207327127456665, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 4.6026, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.3324851569126378, | |
| "grad_norm": 0.7868151068687439, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 4.6185, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.3341815097540288, | |
| "grad_norm": 0.9098244309425354, | |
| "learning_rate": 6.150154258476315e-08, | |
| "loss": 4.6184, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.33587786259541985, | |
| "grad_norm": 1.2755544185638428, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 4.6108, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.3375742154368109, | |
| "grad_norm": 1.315685749053955, | |
| "learning_rate": 6.834750376549792e-09, | |
| "loss": 4.6215, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.33927056827820185, | |
| "grad_norm": 1.5224822759628296, | |
| "learning_rate": 0.0, | |
| "loss": 4.6496, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33927056827820185, | |
| "eval_loss": 4.617598533630371, | |
| "eval_runtime": 56.6116, | |
| "eval_samples_per_second": 17.541, | |
| "eval_steps_per_second": 4.398, | |
| "step": 200 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0733999264838451e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |