| { | |
| "best_metric": 0.04871680587530136, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.026428516369162325, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00035238021825549767, | |
| "grad_norm": 0.18368496000766754, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.07, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035238021825549767, | |
| "eval_loss": 0.3029957115650177, | |
| "eval_runtime": 5.7325, | |
| "eval_samples_per_second": 8.722, | |
| "eval_steps_per_second": 2.268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007047604365109953, | |
| "grad_norm": 0.40931159257888794, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0927, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001057140654766493, | |
| "grad_norm": 0.46541017293930054, | |
| "learning_rate": 0.0001, | |
| "loss": 0.101, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014095208730219907, | |
| "grad_norm": 0.3590395152568817, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 0.0586, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0017619010912774884, | |
| "grad_norm": 0.9103890061378479, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 0.063, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002114281309532986, | |
| "grad_norm": 0.22858065366744995, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.0388, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0024666615277884837, | |
| "grad_norm": 0.5428525805473328, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 0.0452, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0028190417460439814, | |
| "grad_norm": 0.1322905421257019, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 0.0359, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003171421964299479, | |
| "grad_norm": 0.2533002495765686, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.0429, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0035238021825549767, | |
| "grad_norm": 0.15599848330020905, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.0426, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0038761824008104744, | |
| "grad_norm": 0.13487255573272705, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.0465, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004228562619065972, | |
| "grad_norm": 0.14608468115329742, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.0574, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00458094283732147, | |
| "grad_norm": 0.37514936923980713, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.0393, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004933323055576967, | |
| "grad_norm": 0.09332629293203354, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.0262, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0052857032738324655, | |
| "grad_norm": 0.04472605511546135, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.0165, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005638083492087963, | |
| "grad_norm": 0.04193398728966713, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.0166, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005990463710343461, | |
| "grad_norm": 0.06309419125318527, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.0194, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006342843928598958, | |
| "grad_norm": 0.049311138689517975, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.022, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006695224146854456, | |
| "grad_norm": 0.033052124083042145, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.0277, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007047604365109953, | |
| "grad_norm": 0.047948189079761505, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.0308, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0073999845833654515, | |
| "grad_norm": 0.09758961200714111, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0334, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007752364801620949, | |
| "grad_norm": 0.08111658692359924, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.0375, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008104745019876446, | |
| "grad_norm": 0.10492856800556183, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0447, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008457125238131944, | |
| "grad_norm": 0.27334481477737427, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.0558, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008809505456387442, | |
| "grad_norm": 0.09733742475509644, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.0646, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008809505456387442, | |
| "eval_loss": 0.05434239283204079, | |
| "eval_runtime": 5.835, | |
| "eval_samples_per_second": 8.569, | |
| "eval_steps_per_second": 2.228, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00916188567464294, | |
| "grad_norm": 0.1138065904378891, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 0.0288, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.009514265892898437, | |
| "grad_norm": 0.13079240918159485, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.0152, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009866646111153935, | |
| "grad_norm": 0.16374854743480682, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 0.0212, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010219026329409433, | |
| "grad_norm": 0.09367111325263977, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 0.0222, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.010571406547664931, | |
| "grad_norm": 0.027064498513936996, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0222, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010923786765920427, | |
| "grad_norm": 0.12557287514209747, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0284, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.011276166984175925, | |
| "grad_norm": 0.14048165082931519, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 0.0319, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011628547202431424, | |
| "grad_norm": 0.1092550978064537, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0327, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011980927420686922, | |
| "grad_norm": 0.05221077799797058, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 0.037, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.012333307638942418, | |
| "grad_norm": 0.04570182412862778, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0403, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012685687857197916, | |
| "grad_norm": 0.12411309778690338, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0467, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013038068075453414, | |
| "grad_norm": 0.09028882533311844, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.0558, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.013390448293708912, | |
| "grad_norm": 0.20290955901145935, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 0.0216, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.01374282851196441, | |
| "grad_norm": 0.040300991386175156, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0202, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014095208730219907, | |
| "grad_norm": 0.014306614175438881, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 0.0137, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014447588948475405, | |
| "grad_norm": 0.02834320440888405, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 0.0183, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.014799969166730903, | |
| "grad_norm": 0.01949421875178814, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0196, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.015152349384986401, | |
| "grad_norm": 0.03610558062791824, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.024, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.015504729603241897, | |
| "grad_norm": 0.039888154715299606, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 0.0262, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.015857109821497396, | |
| "grad_norm": 0.0371965691447258, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0282, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.016209490039752892, | |
| "grad_norm": 0.038961343467235565, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 0.0355, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.016561870258008392, | |
| "grad_norm": 0.045494209975004196, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0383, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.016914250476263888, | |
| "grad_norm": 0.05365985259413719, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.044, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.017266630694519388, | |
| "grad_norm": 0.0467500165104866, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.0511, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.017619010912774884, | |
| "grad_norm": 0.07677899301052094, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.0697, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.017619010912774884, | |
| "eval_loss": 0.05016423761844635, | |
| "eval_runtime": 5.5589, | |
| "eval_samples_per_second": 8.995, | |
| "eval_steps_per_second": 2.339, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01797139113103038, | |
| "grad_norm": 0.05385514348745346, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0233, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01832377134928588, | |
| "grad_norm": 0.05782073363661766, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 0.0122, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.018676151567541377, | |
| "grad_norm": 0.0645056962966919, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 0.0168, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.019028531785796873, | |
| "grad_norm": 0.07855939865112305, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0207, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.019380912004052373, | |
| "grad_norm": 0.07800403237342834, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 0.0227, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01973329222230787, | |
| "grad_norm": 0.060954831540584564, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 0.0237, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.02008567244056337, | |
| "grad_norm": 0.04431851580739021, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0264, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.020438052658818866, | |
| "grad_norm": 0.033269140869379044, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 0.0316, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.020790432877074362, | |
| "grad_norm": 0.01977214589715004, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.0318, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.021142813095329862, | |
| "grad_norm": 0.03904677554965019, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0402, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02149519331358536, | |
| "grad_norm": 0.10086186975240707, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 0.0493, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.021847573531840855, | |
| "grad_norm": 0.1489732712507248, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 0.0598, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.022199953750096355, | |
| "grad_norm": 0.06647814810276031, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0266, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.02255233396835185, | |
| "grad_norm": 0.033716265112161636, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 0.0177, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.02290471418660735, | |
| "grad_norm": 0.01775234565138817, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 0.0125, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.023257094404862847, | |
| "grad_norm": 0.013323824852705002, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0178, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.023609474623118343, | |
| "grad_norm": 0.02086944319307804, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.0187, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.023961854841373843, | |
| "grad_norm": 0.019485145807266235, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 0.0246, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.02431423505962934, | |
| "grad_norm": 0.00897766649723053, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0277, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.024666615277884836, | |
| "grad_norm": 0.014582326635718346, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 0.0299, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.025018995496140336, | |
| "grad_norm": 0.029548194259405136, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.0331, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.025371375714395832, | |
| "grad_norm": 0.03517298772931099, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0361, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.025723755932651332, | |
| "grad_norm": 0.026599425822496414, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 0.0432, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.02607613615090683, | |
| "grad_norm": 0.022014496847987175, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 0.0471, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.026428516369162325, | |
| "grad_norm": 0.07925083488225937, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0657, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.026428516369162325, | |
| "eval_loss": 0.04871680587530136, | |
| "eval_runtime": 5.8192, | |
| "eval_samples_per_second": 8.592, | |
| "eval_steps_per_second": 2.234, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 9.559191436625183e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |