| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04340748779164406, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004340748779164406, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004340748779164406, | |
| "eval_loss": NaN, | |
| "eval_runtime": 413.2144, | |
| "eval_samples_per_second": 9.39, | |
| "eval_steps_per_second": 2.347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008681497558328812, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013022246337493217, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017362995116657625, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002170374389582203, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0026044492674986435, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003038524145415084, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003472599023331525, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003906673901247965, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004340748779164406, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004774823657080846, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.005208898534997287, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005642973412913727, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006077048290830168, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0065111231687466084, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00694519804666305, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00737927292457949, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00781334780249593, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008247422680412371, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008681497558328812, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009115572436245252, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009549647314161693, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009983722192078133, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.010417797069994574, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010851871947911014, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011285946825827455, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011720021703743895, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012154096581660336, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012588171459576776, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.013022246337493217, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013456321215409657, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0138903960933261, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01432447097124254, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01475854584915898, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.015192620727075421, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01562669560499186, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.016060770482908302, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.016494845360824743, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.016928920238741183, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.017362995116657624, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017797069994574064, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.018231144872490505, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.018665219750406945, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.019099294628323386, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.019533369506239826, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.019967444384156267, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.020401519262072707, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.020835594139989148, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.021269669017905588, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02170374389582203, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02170374389582203, | |
| "eval_loss": NaN, | |
| "eval_runtime": 414.1606, | |
| "eval_samples_per_second": 9.368, | |
| "eval_steps_per_second": 2.342, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02213781877373847, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.02257189365165491, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02300596852957135, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.02344004340748779, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.02387411828540423, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02430819316332067, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.024742268041237112, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.025176342919153553, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.025610417797069993, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.026044492674986434, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.026478567552902874, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.026912642430819315, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.027346717308735755, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0277807921866522, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.02821486706456864, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.02864894194248508, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.02908301682040152, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.02951709169831796, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.029951166576234402, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.030385241454150842, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.030819316332067283, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.03125339120998372, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.031687466087900164, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.032121540965816604, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.032555615843733045, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.032989690721649485, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.033423765599565926, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.033857840477482366, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.03429191535539881, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.03472599023331525, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03516006511123169, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.03559413998914813, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.03602821486706457, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.03646228974498101, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.03689636462289745, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03733043950081389, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.03776451437873033, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.03819858925664677, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.03863266413456321, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.03906673901247965, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03950081389039609, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.03993488876831253, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.040368963646228974, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.040803038524145414, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.041671188279978295, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.042539338035811176, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.04297341291372762, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.04340748779164406, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04340748779164406, | |
| "eval_loss": NaN, | |
| "eval_runtime": 414.9261, | |
| "eval_samples_per_second": 9.351, | |
| "eval_steps_per_second": 2.338, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.301575974354944e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |