| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.00729860414195785, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.298604141957851e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 16.5325, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.298604141957851e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 414.8848, | |
| "eval_samples_per_second": 55.62, | |
| "eval_steps_per_second": 13.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014597208283915702, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021895812425873552, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029194416567831404, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003649302070978925, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00043791624851747103, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005109022899370496, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005838883313566281, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006568743727762066, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000729860414195785, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008028464556153635, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008758324970349421, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009488185384545206, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0010218045798740991, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010947906212936775, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011677766627132562, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012407627041328346, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0013137487455524132, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013867347869719916, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00145972082839157, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015327068698111487, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001605692911230727, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0016786789526503057, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0017516649940698841, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0018246510354894625, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018976370769090412, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00197062311832862, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0020436091597481982, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0021165952011677766, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002189581242587355, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022625672840069335, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0023355533254265123, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0024085393668460907, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.002481525408265669, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0025545114496852476, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0026274974911048264, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.002700483532524405, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0027734695739439832, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0028464556153635617, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00291944165678314, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002992427698202719, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0030654137396222973, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0031383997810418758, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.003211385822461454, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0032843718638810326, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0033573579053006114, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00343034394672019, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0035033299881397683, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0035763160295593467, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.003649302070978925, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003649302070978925, | |
| "eval_loss": NaN, | |
| "eval_runtime": 413.9935, | |
| "eval_samples_per_second": 55.74, | |
| "eval_steps_per_second": 13.935, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003722288112398504, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.847932752400164e-06, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0037952741538180824, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.761321158169134e-06, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0038682601952376608, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6743911843603134e-06, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.00394124623665724, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.587248741756253e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.004014232278076818, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0040872183194963965, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4127512582437486e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.004160204360915975, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.325608815639687e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.004233190402335553, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.238678841830867e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.004306176443755132, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1520672475998374e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.00437916248517471, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0658795558326745e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0044521485265942885, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9802207729556023e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.004525134568013867, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.895195261000831e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.004598120609433446, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8109066104575023e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.004671106650853025, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.004744092692272603, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6449496416858285e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0048170787336921815, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.56348351646022e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.00489006477511176, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4831583923105e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.004963050816531338, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4040721330273063e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.005036036857950917, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3263210930352737e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.005109022899370495, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2500000000000007e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0051820089407900735, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1752018394169882e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.005254994982209653, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1020177413231334e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.005327981023629231, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.00540096706504881, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.608463116858544e-07, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.005473953106468388, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.930309757836517e-07, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0055469391478879665, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.271734841028553e-07, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.005619925189307545, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.633540738525066e-07, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.005692911230727123, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.016504991533727e-07, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.005765897272146702, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.421379363065142e-07, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.00583888331356628, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.848888922025553e-07, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005911869354985859, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.299731159831953e-07, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.005984855396405438, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.006057841437825016, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.27406068612396e-07, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.006130827479244595, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798797596089351e-07, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.006203813520664173, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3493649053890325e-07, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.0062767995620837515, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9263101785268253e-07, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.00634978560350333, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53014884252083e-07, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.006422771644922908, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1613635589349756e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.006495757686342487, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8204036358303173e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.006568743727762065, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.507684480352292e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006641729769181644, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.006714715810601223, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.684576015420277e-08, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.006787701852020801, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.426068431000883e-08, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.00686068789344038, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.463099816548578e-08, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.006933673934859958, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.798061746947995e-08, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0070066599762795365, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4329828146074096e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.007079646017699115, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3695261579316776e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.007152632059118693, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.089874350439507e-09, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.007225618100538272, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5229324522605949e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.00729860414195785, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00729860414195785, | |
| "eval_loss": NaN, | |
| "eval_runtime": 414.6472, | |
| "eval_samples_per_second": 55.652, | |
| "eval_steps_per_second": 13.913, | |
| "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": 7804330306437120.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |