{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 1722, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0017436791630340018, "grad_norm": 3.576176404953003, "learning_rate": 0.0, "loss": 1.1624, "step": 1 }, { "epoch": 0.0034873583260680036, "grad_norm": 3.429298162460327, "learning_rate": 2e-05, "loss": 1.3068, "step": 2 }, { "epoch": 0.0052310374891020054, "grad_norm": 1.881797194480896, "learning_rate": 4e-05, "loss": 0.9927, "step": 3 }, { "epoch": 0.006974716652136007, "grad_norm": 1.7390609979629517, "learning_rate": 6e-05, "loss": 1.2225, "step": 4 }, { "epoch": 0.008718395815170008, "grad_norm": 1.9693503379821777, "learning_rate": 8e-05, "loss": 1.1007, "step": 5 }, { "epoch": 0.010462074978204011, "grad_norm": 1.3608834743499756, "learning_rate": 0.0001, "loss": 0.8612, "step": 6 }, { "epoch": 0.012205754141238012, "grad_norm": 1.42159903049469, "learning_rate": 9.994175888177053e-05, "loss": 0.9414, "step": 7 }, { "epoch": 0.013949433304272014, "grad_norm": 1.4977730512619019, "learning_rate": 9.988351776354107e-05, "loss": 1.0214, "step": 8 }, { "epoch": 0.015693112467306015, "grad_norm": 1.2602367401123047, "learning_rate": 9.98252766453116e-05, "loss": 0.9988, "step": 9 }, { "epoch": 0.017436791630340016, "grad_norm": 1.1592556238174438, "learning_rate": 9.976703552708213e-05, "loss": 0.9794, "step": 10 }, { "epoch": 0.01918047079337402, "grad_norm": 1.0674638748168945, "learning_rate": 9.970879440885265e-05, "loss": 0.9544, "step": 11 }, { "epoch": 0.020924149956408022, "grad_norm": 1.2949107885360718, "learning_rate": 9.965055329062318e-05, "loss": 1.0329, "step": 12 }, { "epoch": 0.022667829119442023, "grad_norm": 1.0136593580245972, "learning_rate": 9.959231217239372e-05, "loss": 0.9, "step": 13 }, { "epoch": 0.024411508282476024, "grad_norm": 0.8198906183242798, "learning_rate": 9.953407105416425e-05, "loss": 0.8228, "step": 14 }, { "epoch": 0.026155187445510025, "grad_norm": 1.337257742881775, "learning_rate": 9.947582993593477e-05, "loss": 0.9421, "step": 15 }, { "epoch": 0.02789886660854403, "grad_norm": 1.155364990234375, "learning_rate": 9.941758881770531e-05, "loss": 1.0043, "step": 16 }, { "epoch": 0.02964254577157803, "grad_norm": 1.0972882509231567, "learning_rate": 9.935934769947584e-05, "loss": 1.0206, "step": 17 }, { "epoch": 0.03138622493461203, "grad_norm": 1.062591791152954, "learning_rate": 9.930110658124635e-05, "loss": 1.0244, "step": 18 }, { "epoch": 0.03312990409764603, "grad_norm": 2.394544839859009, "learning_rate": 9.92428654630169e-05, "loss": 0.9876, "step": 19 }, { "epoch": 0.03487358326068003, "grad_norm": 0.8899822235107422, "learning_rate": 9.918462434478742e-05, "loss": 0.8034, "step": 20 }, { "epoch": 0.036617262423714034, "grad_norm": 0.8986620306968689, "learning_rate": 9.912638322655795e-05, "loss": 0.8688, "step": 21 }, { "epoch": 0.03836094158674804, "grad_norm": 0.8343245983123779, "learning_rate": 9.906814210832849e-05, "loss": 0.8708, "step": 22 }, { "epoch": 0.04010462074978204, "grad_norm": 1.0641682147979736, "learning_rate": 9.900990099009902e-05, "loss": 0.9143, "step": 23 }, { "epoch": 0.041848299912816043, "grad_norm": 0.9533904790878296, "learning_rate": 9.895165987186954e-05, "loss": 0.7908, "step": 24 }, { "epoch": 0.043591979075850044, "grad_norm": 1.041989803314209, "learning_rate": 9.889341875364007e-05, "loss": 0.9399, "step": 25 }, { "epoch": 0.045335658238884045, "grad_norm": 0.8525260090827942, "learning_rate": 9.88351776354106e-05, "loss": 0.9168, "step": 26 }, { "epoch": 0.047079337401918046, "grad_norm": 1.189597725868225, "learning_rate": 9.877693651718114e-05, "loss": 1.027, "step": 27 }, { "epoch": 0.04882301656495205, "grad_norm": 0.7804626226425171, "learning_rate": 9.871869539895166e-05, "loss": 0.762, "step": 28 }, { "epoch": 0.05056669572798605, "grad_norm": 1.224485158920288, "learning_rate": 9.866045428072219e-05, "loss": 1.0472, "step": 29 }, { "epoch": 0.05231037489102005, "grad_norm": 0.850109875202179, "learning_rate": 9.860221316249273e-05, "loss": 0.8929, "step": 30 }, { "epoch": 0.05405405405405406, "grad_norm": 1.0351852178573608, "learning_rate": 9.854397204426326e-05, "loss": 0.9702, "step": 31 }, { "epoch": 0.05579773321708806, "grad_norm": 0.9216817617416382, "learning_rate": 9.848573092603379e-05, "loss": 0.8496, "step": 32 }, { "epoch": 0.05754141238012206, "grad_norm": 1.0586507320404053, "learning_rate": 9.842748980780431e-05, "loss": 1.0208, "step": 33 }, { "epoch": 0.05928509154315606, "grad_norm": 0.8114866614341736, "learning_rate": 9.836924868957484e-05, "loss": 0.8677, "step": 34 }, { "epoch": 0.06102877070619006, "grad_norm": 0.8869838118553162, "learning_rate": 9.831100757134537e-05, "loss": 0.8891, "step": 35 }, { "epoch": 0.06277244986922406, "grad_norm": 1.0436128377914429, "learning_rate": 9.825276645311591e-05, "loss": 0.8999, "step": 36 }, { "epoch": 0.06451612903225806, "grad_norm": 0.7940793633460999, "learning_rate": 9.819452533488643e-05, "loss": 0.8159, "step": 37 }, { "epoch": 0.06625980819529206, "grad_norm": 1.0813801288604736, "learning_rate": 9.813628421665696e-05, "loss": 1.0574, "step": 38 }, { "epoch": 0.06800348735832606, "grad_norm": 0.8375930786132812, "learning_rate": 9.80780430984275e-05, "loss": 0.8136, "step": 39 }, { "epoch": 0.06974716652136007, "grad_norm": 0.9363890886306763, "learning_rate": 9.801980198019803e-05, "loss": 0.9677, "step": 40 }, { "epoch": 0.07149084568439407, "grad_norm": 0.8523011207580566, "learning_rate": 9.796156086196856e-05, "loss": 0.91, "step": 41 }, { "epoch": 0.07323452484742807, "grad_norm": 0.8771582245826721, "learning_rate": 9.790331974373908e-05, "loss": 0.8915, "step": 42 }, { "epoch": 0.07497820401046207, "grad_norm": 0.9575395584106445, "learning_rate": 9.784507862550961e-05, "loss": 0.9189, "step": 43 }, { "epoch": 0.07672188317349608, "grad_norm": 1.185190200805664, "learning_rate": 9.778683750728015e-05, "loss": 0.9694, "step": 44 }, { "epoch": 0.07846556233653008, "grad_norm": 1.068806529045105, "learning_rate": 9.772859638905068e-05, "loss": 1.0185, "step": 45 }, { "epoch": 0.08020924149956409, "grad_norm": 0.7363073229789734, "learning_rate": 9.76703552708212e-05, "loss": 0.8123, "step": 46 }, { "epoch": 0.08195292066259809, "grad_norm": 0.9255378246307373, "learning_rate": 9.761211415259174e-05, "loss": 0.8988, "step": 47 }, { "epoch": 0.08369659982563209, "grad_norm": 0.7329453825950623, "learning_rate": 9.755387303436227e-05, "loss": 0.8047, "step": 48 }, { "epoch": 0.08544027898866609, "grad_norm": 0.7093257308006287, "learning_rate": 9.749563191613278e-05, "loss": 0.8321, "step": 49 }, { "epoch": 0.08718395815170009, "grad_norm": 0.8421164155006409, "learning_rate": 9.743739079790332e-05, "loss": 0.8533, "step": 50 }, { "epoch": 0.08892763731473409, "grad_norm": 0.9251890778541565, "learning_rate": 9.737914967967385e-05, "loss": 0.8987, "step": 51 }, { "epoch": 0.09067131647776809, "grad_norm": 0.9134483337402344, "learning_rate": 9.732090856144438e-05, "loss": 0.9334, "step": 52 }, { "epoch": 0.09241499564080209, "grad_norm": 0.7036784291267395, "learning_rate": 9.726266744321492e-05, "loss": 0.7763, "step": 53 }, { "epoch": 0.09415867480383609, "grad_norm": 0.7977387309074402, "learning_rate": 9.720442632498545e-05, "loss": 0.8671, "step": 54 }, { "epoch": 0.0959023539668701, "grad_norm": 0.74471116065979, "learning_rate": 9.714618520675599e-05, "loss": 0.8023, "step": 55 }, { "epoch": 0.0976460331299041, "grad_norm": 0.9310735464096069, "learning_rate": 9.70879440885265e-05, "loss": 0.8589, "step": 56 }, { "epoch": 0.0993897122929381, "grad_norm": 0.8541602492332458, "learning_rate": 9.702970297029703e-05, "loss": 0.8722, "step": 57 }, { "epoch": 0.1011333914559721, "grad_norm": 0.77107173204422, "learning_rate": 9.697146185206757e-05, "loss": 0.8387, "step": 58 }, { "epoch": 0.1028770706190061, "grad_norm": 0.7157709002494812, "learning_rate": 9.69132207338381e-05, "loss": 0.8262, "step": 59 }, { "epoch": 0.1046207497820401, "grad_norm": 0.7679712772369385, "learning_rate": 9.685497961560862e-05, "loss": 0.8476, "step": 60 }, { "epoch": 0.10636442894507411, "grad_norm": 0.7246842980384827, "learning_rate": 9.679673849737916e-05, "loss": 0.8616, "step": 61 }, { "epoch": 0.10810810810810811, "grad_norm": 0.8660008311271667, "learning_rate": 9.673849737914969e-05, "loss": 0.9234, "step": 62 }, { "epoch": 0.10985178727114212, "grad_norm": 0.7798001170158386, "learning_rate": 9.668025626092022e-05, "loss": 0.898, "step": 63 }, { "epoch": 0.11159546643417612, "grad_norm": 0.76876300573349, "learning_rate": 9.662201514269074e-05, "loss": 0.8213, "step": 64 }, { "epoch": 0.11333914559721012, "grad_norm": 0.9286071062088013, "learning_rate": 9.656377402446127e-05, "loss": 0.9852, "step": 65 }, { "epoch": 0.11508282476024412, "grad_norm": 0.9508360624313354, "learning_rate": 9.65055329062318e-05, "loss": 0.9848, "step": 66 }, { "epoch": 0.11682650392327812, "grad_norm": 0.8114030361175537, "learning_rate": 9.644729178800234e-05, "loss": 0.8803, "step": 67 }, { "epoch": 0.11857018308631212, "grad_norm": 0.7688694596290588, "learning_rate": 9.638905066977286e-05, "loss": 0.8498, "step": 68 }, { "epoch": 0.12031386224934612, "grad_norm": 1.3020015954971313, "learning_rate": 9.63308095515434e-05, "loss": 1.0065, "step": 69 }, { "epoch": 0.12205754141238012, "grad_norm": 0.9737802147865295, "learning_rate": 9.627256843331393e-05, "loss": 0.9689, "step": 70 }, { "epoch": 0.12380122057541412, "grad_norm": 1.1209052801132202, "learning_rate": 9.621432731508446e-05, "loss": 0.9085, "step": 71 }, { "epoch": 0.12554489973844812, "grad_norm": 0.8690237998962402, "learning_rate": 9.615608619685498e-05, "loss": 0.9185, "step": 72 }, { "epoch": 0.12728857890148212, "grad_norm": 1.027158260345459, "learning_rate": 9.609784507862551e-05, "loss": 0.9161, "step": 73 }, { "epoch": 0.12903225806451613, "grad_norm": 1.0347217321395874, "learning_rate": 9.603960396039604e-05, "loss": 0.9799, "step": 74 }, { "epoch": 0.13077593722755013, "grad_norm": 0.7429322600364685, "learning_rate": 9.598136284216658e-05, "loss": 0.868, "step": 75 }, { "epoch": 0.13251961639058413, "grad_norm": 0.7140623331069946, "learning_rate": 9.59231217239371e-05, "loss": 0.7988, "step": 76 }, { "epoch": 0.13426329555361813, "grad_norm": 0.864453911781311, "learning_rate": 9.586488060570763e-05, "loss": 0.8808, "step": 77 }, { "epoch": 0.13600697471665213, "grad_norm": 0.7349904775619507, "learning_rate": 9.580663948747817e-05, "loss": 0.8052, "step": 78 }, { "epoch": 0.13775065387968613, "grad_norm": 0.9776052832603455, "learning_rate": 9.574839836924869e-05, "loss": 0.8975, "step": 79 }, { "epoch": 0.13949433304272013, "grad_norm": 1.2594671249389648, "learning_rate": 9.569015725101921e-05, "loss": 0.7602, "step": 80 }, { "epoch": 0.14123801220575413, "grad_norm": 0.9175557494163513, "learning_rate": 9.563191613278975e-05, "loss": 0.8958, "step": 81 }, { "epoch": 0.14298169136878813, "grad_norm": 1.0652610063552856, "learning_rate": 9.557367501456028e-05, "loss": 0.8782, "step": 82 }, { "epoch": 0.14472537053182213, "grad_norm": 1.0092709064483643, "learning_rate": 9.551543389633082e-05, "loss": 0.9237, "step": 83 }, { "epoch": 0.14646904969485613, "grad_norm": 0.727262020111084, "learning_rate": 9.545719277810135e-05, "loss": 0.8538, "step": 84 }, { "epoch": 0.14821272885789014, "grad_norm": 0.8211482763290405, "learning_rate": 9.539895165987187e-05, "loss": 0.8636, "step": 85 }, { "epoch": 0.14995640802092414, "grad_norm": 1.040635585784912, "learning_rate": 9.53407105416424e-05, "loss": 0.8884, "step": 86 }, { "epoch": 0.15170008718395817, "grad_norm": 0.7466046810150146, "learning_rate": 9.528246942341293e-05, "loss": 0.8364, "step": 87 }, { "epoch": 0.15344376634699217, "grad_norm": 0.9494810700416565, "learning_rate": 9.522422830518346e-05, "loss": 0.9733, "step": 88 }, { "epoch": 0.15518744551002617, "grad_norm": 0.754625141620636, "learning_rate": 9.5165987186954e-05, "loss": 0.8464, "step": 89 }, { "epoch": 0.15693112467306017, "grad_norm": 0.9390312433242798, "learning_rate": 9.510774606872452e-05, "loss": 0.9476, "step": 90 }, { "epoch": 0.15867480383609417, "grad_norm": 0.783344030380249, "learning_rate": 9.504950495049505e-05, "loss": 0.8946, "step": 91 }, { "epoch": 0.16041848299912817, "grad_norm": 0.8624845743179321, "learning_rate": 9.499126383226559e-05, "loss": 0.9307, "step": 92 }, { "epoch": 0.16216216216216217, "grad_norm": 0.7479653358459473, "learning_rate": 9.493302271403612e-05, "loss": 0.8325, "step": 93 }, { "epoch": 0.16390584132519617, "grad_norm": 0.9143496155738831, "learning_rate": 9.487478159580664e-05, "loss": 0.8298, "step": 94 }, { "epoch": 0.16564952048823017, "grad_norm": 0.7612428665161133, "learning_rate": 9.481654047757717e-05, "loss": 0.8509, "step": 95 }, { "epoch": 0.16739319965126417, "grad_norm": 0.8277957439422607, "learning_rate": 9.47582993593477e-05, "loss": 0.9046, "step": 96 }, { "epoch": 0.16913687881429817, "grad_norm": 0.8976776599884033, "learning_rate": 9.470005824111824e-05, "loss": 0.8247, "step": 97 }, { "epoch": 0.17088055797733218, "grad_norm": 0.7536888122558594, "learning_rate": 9.464181712288877e-05, "loss": 0.8304, "step": 98 }, { "epoch": 0.17262423714036618, "grad_norm": 0.8665176630020142, "learning_rate": 9.458357600465929e-05, "loss": 0.9234, "step": 99 }, { "epoch": 0.17436791630340018, "grad_norm": 0.9990089535713196, "learning_rate": 9.452533488642983e-05, "loss": 1.0261, "step": 100 }, { "epoch": 0.17611159546643418, "grad_norm": 0.6755781173706055, "learning_rate": 9.446709376820036e-05, "loss": 0.8685, "step": 101 }, { "epoch": 0.17785527462946818, "grad_norm": 0.7537196278572083, "learning_rate": 9.440885264997089e-05, "loss": 0.8148, "step": 102 }, { "epoch": 0.17959895379250218, "grad_norm": 0.8158227205276489, "learning_rate": 9.435061153174141e-05, "loss": 0.8603, "step": 103 }, { "epoch": 0.18134263295553618, "grad_norm": 0.93252032995224, "learning_rate": 9.429237041351194e-05, "loss": 0.931, "step": 104 }, { "epoch": 0.18308631211857018, "grad_norm": 0.9715843796730042, "learning_rate": 9.423412929528247e-05, "loss": 0.8531, "step": 105 }, { "epoch": 0.18482999128160418, "grad_norm": 0.8752953410148621, "learning_rate": 9.417588817705301e-05, "loss": 0.8523, "step": 106 }, { "epoch": 0.18657367044463818, "grad_norm": 0.8178887963294983, "learning_rate": 9.411764705882353e-05, "loss": 0.9251, "step": 107 }, { "epoch": 0.18831734960767219, "grad_norm": 0.6982199549674988, "learning_rate": 9.405940594059406e-05, "loss": 0.8759, "step": 108 }, { "epoch": 0.1900610287707062, "grad_norm": 0.7332287430763245, "learning_rate": 9.40011648223646e-05, "loss": 0.8538, "step": 109 }, { "epoch": 0.1918047079337402, "grad_norm": 0.7943186163902283, "learning_rate": 9.394292370413512e-05, "loss": 0.9086, "step": 110 }, { "epoch": 0.1935483870967742, "grad_norm": 0.9489659070968628, "learning_rate": 9.388468258590566e-05, "loss": 0.8955, "step": 111 }, { "epoch": 0.1952920662598082, "grad_norm": 0.735752522945404, "learning_rate": 9.382644146767618e-05, "loss": 0.79, "step": 112 }, { "epoch": 0.1970357454228422, "grad_norm": 0.767719566822052, "learning_rate": 9.376820034944671e-05, "loss": 0.9254, "step": 113 }, { "epoch": 0.1987794245858762, "grad_norm": 0.8199548125267029, "learning_rate": 9.370995923121725e-05, "loss": 0.7882, "step": 114 }, { "epoch": 0.2005231037489102, "grad_norm": 0.6511307954788208, "learning_rate": 9.365171811298778e-05, "loss": 0.8032, "step": 115 }, { "epoch": 0.2022667829119442, "grad_norm": 0.8873404264450073, "learning_rate": 9.35934769947583e-05, "loss": 0.8377, "step": 116 }, { "epoch": 0.2040104620749782, "grad_norm": 0.8010528683662415, "learning_rate": 9.353523587652883e-05, "loss": 0.8791, "step": 117 }, { "epoch": 0.2057541412380122, "grad_norm": 0.8364830017089844, "learning_rate": 9.347699475829936e-05, "loss": 0.845, "step": 118 }, { "epoch": 0.2074978204010462, "grad_norm": 0.6978510618209839, "learning_rate": 9.341875364006988e-05, "loss": 0.862, "step": 119 }, { "epoch": 0.2092414995640802, "grad_norm": 1.134799599647522, "learning_rate": 9.336051252184043e-05, "loss": 1.0674, "step": 120 }, { "epoch": 0.2109851787271142, "grad_norm": 0.9052099585533142, "learning_rate": 9.330227140361095e-05, "loss": 0.8621, "step": 121 }, { "epoch": 0.21272885789014823, "grad_norm": 0.8365368843078613, "learning_rate": 9.324403028538148e-05, "loss": 0.9168, "step": 122 }, { "epoch": 0.21447253705318223, "grad_norm": 0.9175293445587158, "learning_rate": 9.318578916715202e-05, "loss": 0.9049, "step": 123 }, { "epoch": 0.21621621621621623, "grad_norm": 1.0795987844467163, "learning_rate": 9.312754804892255e-05, "loss": 1.0633, "step": 124 }, { "epoch": 0.21795989537925023, "grad_norm": 0.9198187589645386, "learning_rate": 9.306930693069307e-05, "loss": 0.9388, "step": 125 }, { "epoch": 0.21970357454228423, "grad_norm": 0.7457751035690308, "learning_rate": 9.30110658124636e-05, "loss": 0.8425, "step": 126 }, { "epoch": 0.22144725370531823, "grad_norm": 0.6850293278694153, "learning_rate": 9.295282469423413e-05, "loss": 0.8454, "step": 127 }, { "epoch": 0.22319093286835223, "grad_norm": 0.8800644874572754, "learning_rate": 9.289458357600467e-05, "loss": 0.8753, "step": 128 }, { "epoch": 0.22493461203138623, "grad_norm": 0.7765899896621704, "learning_rate": 9.28363424577752e-05, "loss": 0.8687, "step": 129 }, { "epoch": 0.22667829119442023, "grad_norm": 0.6896671652793884, "learning_rate": 9.277810133954572e-05, "loss": 0.7933, "step": 130 }, { "epoch": 0.22842197035745423, "grad_norm": 0.6559915542602539, "learning_rate": 9.271986022131626e-05, "loss": 0.7803, "step": 131 }, { "epoch": 0.23016564952048824, "grad_norm": 0.6539562940597534, "learning_rate": 9.266161910308679e-05, "loss": 0.8222, "step": 132 }, { "epoch": 0.23190932868352224, "grad_norm": 0.8717973828315735, "learning_rate": 9.260337798485732e-05, "loss": 0.9522, "step": 133 }, { "epoch": 0.23365300784655624, "grad_norm": 0.7323669195175171, "learning_rate": 9.254513686662784e-05, "loss": 0.8619, "step": 134 }, { "epoch": 0.23539668700959024, "grad_norm": 0.8358727097511292, "learning_rate": 9.248689574839837e-05, "loss": 0.8786, "step": 135 }, { "epoch": 0.23714036617262424, "grad_norm": 0.8474705815315247, "learning_rate": 9.24286546301689e-05, "loss": 0.9132, "step": 136 }, { "epoch": 0.23888404533565824, "grad_norm": 0.8468974232673645, "learning_rate": 9.237041351193944e-05, "loss": 0.9117, "step": 137 }, { "epoch": 0.24062772449869224, "grad_norm": 0.9936217069625854, "learning_rate": 9.231217239370996e-05, "loss": 0.8978, "step": 138 }, { "epoch": 0.24237140366172624, "grad_norm": 0.7764740586280823, "learning_rate": 9.22539312754805e-05, "loss": 0.8381, "step": 139 }, { "epoch": 0.24411508282476024, "grad_norm": 0.7599921226501465, "learning_rate": 9.219569015725103e-05, "loss": 0.8259, "step": 140 }, { "epoch": 0.24585876198779424, "grad_norm": 0.6565180420875549, "learning_rate": 9.213744903902154e-05, "loss": 0.8229, "step": 141 }, { "epoch": 0.24760244115082825, "grad_norm": 1.0493465662002563, "learning_rate": 9.207920792079209e-05, "loss": 0.9247, "step": 142 }, { "epoch": 0.24934612031386225, "grad_norm": 1.0720256567001343, "learning_rate": 9.202096680256261e-05, "loss": 0.994, "step": 143 }, { "epoch": 0.25108979947689625, "grad_norm": 0.908941388130188, "learning_rate": 9.196272568433314e-05, "loss": 1.0302, "step": 144 }, { "epoch": 0.2528334786399303, "grad_norm": 0.8322412371635437, "learning_rate": 9.190448456610368e-05, "loss": 0.9469, "step": 145 }, { "epoch": 0.25457715780296425, "grad_norm": 0.8561587333679199, "learning_rate": 9.18462434478742e-05, "loss": 0.7639, "step": 146 }, { "epoch": 0.2563208369659983, "grad_norm": 0.8225048780441284, "learning_rate": 9.178800232964473e-05, "loss": 0.9195, "step": 147 }, { "epoch": 0.25806451612903225, "grad_norm": 0.7731052041053772, "learning_rate": 9.172976121141526e-05, "loss": 0.8244, "step": 148 }, { "epoch": 0.2598081952920663, "grad_norm": 0.9132447242736816, "learning_rate": 9.167152009318579e-05, "loss": 0.9219, "step": 149 }, { "epoch": 0.26155187445510025, "grad_norm": 1.1405301094055176, "learning_rate": 9.161327897495631e-05, "loss": 1.0154, "step": 150 }, { "epoch": 0.2632955536181343, "grad_norm": 0.9096696972846985, "learning_rate": 9.155503785672685e-05, "loss": 0.9057, "step": 151 }, { "epoch": 0.26503923278116825, "grad_norm": 0.7591986060142517, "learning_rate": 9.149679673849738e-05, "loss": 0.8392, "step": 152 }, { "epoch": 0.2667829119442023, "grad_norm": 0.809049665927887, "learning_rate": 9.143855562026792e-05, "loss": 0.9216, "step": 153 }, { "epoch": 0.26852659110723626, "grad_norm": 0.7896736264228821, "learning_rate": 9.138031450203845e-05, "loss": 0.9034, "step": 154 }, { "epoch": 0.2702702702702703, "grad_norm": 0.8977379202842712, "learning_rate": 9.132207338380898e-05, "loss": 0.9154, "step": 155 }, { "epoch": 0.27201394943330426, "grad_norm": 0.7305199503898621, "learning_rate": 9.12638322655795e-05, "loss": 0.8918, "step": 156 }, { "epoch": 0.2737576285963383, "grad_norm": 0.751531183719635, "learning_rate": 9.120559114735003e-05, "loss": 0.9013, "step": 157 }, { "epoch": 0.27550130775937226, "grad_norm": 0.7157143950462341, "learning_rate": 9.114735002912056e-05, "loss": 0.8606, "step": 158 }, { "epoch": 0.2772449869224063, "grad_norm": 0.6594380736351013, "learning_rate": 9.10891089108911e-05, "loss": 0.8479, "step": 159 }, { "epoch": 0.27898866608544026, "grad_norm": 0.9078890085220337, "learning_rate": 9.103086779266162e-05, "loss": 0.9188, "step": 160 }, { "epoch": 0.2807323452484743, "grad_norm": 0.7843688130378723, "learning_rate": 9.097262667443215e-05, "loss": 0.8232, "step": 161 }, { "epoch": 0.28247602441150826, "grad_norm": 0.7125802636146545, "learning_rate": 9.091438555620269e-05, "loss": 0.8131, "step": 162 }, { "epoch": 0.2842197035745423, "grad_norm": 0.7278924584388733, "learning_rate": 9.085614443797322e-05, "loss": 0.8746, "step": 163 }, { "epoch": 0.28596338273757627, "grad_norm": 0.8192118406295776, "learning_rate": 9.079790331974374e-05, "loss": 0.878, "step": 164 }, { "epoch": 0.2877070619006103, "grad_norm": 1.1749672889709473, "learning_rate": 9.073966220151427e-05, "loss": 1.0946, "step": 165 }, { "epoch": 0.28945074106364427, "grad_norm": 0.7896987795829773, "learning_rate": 9.06814210832848e-05, "loss": 0.9, "step": 166 }, { "epoch": 0.2911944202266783, "grad_norm": 0.7843860983848572, "learning_rate": 9.062317996505534e-05, "loss": 0.8781, "step": 167 }, { "epoch": 0.29293809938971227, "grad_norm": 0.8374670147895813, "learning_rate": 9.056493884682587e-05, "loss": 0.8777, "step": 168 }, { "epoch": 0.2946817785527463, "grad_norm": 1.0037024021148682, "learning_rate": 9.050669772859639e-05, "loss": 0.9612, "step": 169 }, { "epoch": 0.29642545771578027, "grad_norm": 0.6512691974639893, "learning_rate": 9.044845661036693e-05, "loss": 0.8407, "step": 170 }, { "epoch": 0.2981691368788143, "grad_norm": 0.8199954628944397, "learning_rate": 9.039021549213745e-05, "loss": 0.8907, "step": 171 }, { "epoch": 0.2999128160418483, "grad_norm": 0.8234912753105164, "learning_rate": 9.033197437390797e-05, "loss": 0.9254, "step": 172 }, { "epoch": 0.3016564952048823, "grad_norm": 0.6629686951637268, "learning_rate": 9.027373325567851e-05, "loss": 0.8204, "step": 173 }, { "epoch": 0.30340017436791633, "grad_norm": 1.3002822399139404, "learning_rate": 9.021549213744904e-05, "loss": 0.986, "step": 174 }, { "epoch": 0.3051438535309503, "grad_norm": 0.7589675188064575, "learning_rate": 9.015725101921957e-05, "loss": 0.7813, "step": 175 }, { "epoch": 0.30688753269398433, "grad_norm": 0.7604683041572571, "learning_rate": 9.009900990099011e-05, "loss": 0.785, "step": 176 }, { "epoch": 0.3086312118570183, "grad_norm": 0.7062495946884155, "learning_rate": 9.004076878276064e-05, "loss": 0.8096, "step": 177 }, { "epoch": 0.31037489102005233, "grad_norm": 0.8533647060394287, "learning_rate": 8.998252766453116e-05, "loss": 0.8794, "step": 178 }, { "epoch": 0.3121185701830863, "grad_norm": 0.9520115852355957, "learning_rate": 8.992428654630169e-05, "loss": 0.889, "step": 179 }, { "epoch": 0.31386224934612034, "grad_norm": 0.886651337146759, "learning_rate": 8.986604542807222e-05, "loss": 0.8388, "step": 180 }, { "epoch": 0.3156059285091543, "grad_norm": 0.941131591796875, "learning_rate": 8.980780430984276e-05, "loss": 0.8002, "step": 181 }, { "epoch": 0.31734960767218834, "grad_norm": 1.4103411436080933, "learning_rate": 8.974956319161328e-05, "loss": 0.7396, "step": 182 }, { "epoch": 0.3190932868352223, "grad_norm": 0.7787629961967468, "learning_rate": 8.969132207338381e-05, "loss": 0.8359, "step": 183 }, { "epoch": 0.32083696599825634, "grad_norm": 0.6483763456344604, "learning_rate": 8.963308095515435e-05, "loss": 0.7559, "step": 184 }, { "epoch": 0.3225806451612903, "grad_norm": 0.7572669386863708, "learning_rate": 8.957483983692488e-05, "loss": 0.8723, "step": 185 }, { "epoch": 0.32432432432432434, "grad_norm": 0.8219138979911804, "learning_rate": 8.95165987186954e-05, "loss": 0.8234, "step": 186 }, { "epoch": 0.3260680034873583, "grad_norm": 1.1521936655044556, "learning_rate": 8.945835760046593e-05, "loss": 0.9108, "step": 187 }, { "epoch": 0.32781168265039234, "grad_norm": 2.088010311126709, "learning_rate": 8.940011648223646e-05, "loss": 0.877, "step": 188 }, { "epoch": 0.3295553618134263, "grad_norm": 0.8853165507316589, "learning_rate": 8.934187536400699e-05, "loss": 0.8706, "step": 189 }, { "epoch": 0.33129904097646035, "grad_norm": 0.8609984517097473, "learning_rate": 8.928363424577753e-05, "loss": 0.8835, "step": 190 }, { "epoch": 0.3330427201394943, "grad_norm": 0.7566626071929932, "learning_rate": 8.922539312754805e-05, "loss": 0.8571, "step": 191 }, { "epoch": 0.33478639930252835, "grad_norm": 0.7419030070304871, "learning_rate": 8.91671520093186e-05, "loss": 0.8201, "step": 192 }, { "epoch": 0.3365300784655623, "grad_norm": 0.851673424243927, "learning_rate": 8.910891089108912e-05, "loss": 0.9788, "step": 193 }, { "epoch": 0.33827375762859635, "grad_norm": 0.6700695753097534, "learning_rate": 8.905066977285965e-05, "loss": 0.8367, "step": 194 }, { "epoch": 0.3400174367916303, "grad_norm": 0.8057977557182312, "learning_rate": 8.899242865463017e-05, "loss": 0.9105, "step": 195 }, { "epoch": 0.34176111595466435, "grad_norm": 0.7886006832122803, "learning_rate": 8.89341875364007e-05, "loss": 0.7337, "step": 196 }, { "epoch": 0.3435047951176983, "grad_norm": 0.8905133605003357, "learning_rate": 8.887594641817123e-05, "loss": 0.8554, "step": 197 }, { "epoch": 0.34524847428073235, "grad_norm": 0.9094963669776917, "learning_rate": 8.881770529994177e-05, "loss": 0.8655, "step": 198 }, { "epoch": 0.3469921534437663, "grad_norm": 0.7917893528938293, "learning_rate": 8.87594641817123e-05, "loss": 0.8961, "step": 199 }, { "epoch": 0.34873583260680036, "grad_norm": 0.8081362843513489, "learning_rate": 8.870122306348282e-05, "loss": 0.9641, "step": 200 }, { "epoch": 0.35047951176983433, "grad_norm": 0.9641375541687012, "learning_rate": 8.864298194525336e-05, "loss": 0.9251, "step": 201 }, { "epoch": 0.35222319093286836, "grad_norm": 0.9539868831634521, "learning_rate": 8.858474082702388e-05, "loss": 0.981, "step": 202 }, { "epoch": 0.35396687009590233, "grad_norm": 1.0432499647140503, "learning_rate": 8.85264997087944e-05, "loss": 0.9194, "step": 203 }, { "epoch": 0.35571054925893636, "grad_norm": 0.8304929137229919, "learning_rate": 8.846825859056494e-05, "loss": 0.8261, "step": 204 }, { "epoch": 0.35745422842197033, "grad_norm": 0.8569386601448059, "learning_rate": 8.841001747233547e-05, "loss": 0.8982, "step": 205 }, { "epoch": 0.35919790758500436, "grad_norm": 1.036265254020691, "learning_rate": 8.835177635410601e-05, "loss": 1.0141, "step": 206 }, { "epoch": 0.36094158674803833, "grad_norm": 0.9144682288169861, "learning_rate": 8.829353523587654e-05, "loss": 0.9946, "step": 207 }, { "epoch": 0.36268526591107236, "grad_norm": 0.7627949714660645, "learning_rate": 8.823529411764706e-05, "loss": 0.8755, "step": 208 }, { "epoch": 0.3644289450741064, "grad_norm": 0.8703427910804749, "learning_rate": 8.817705299941759e-05, "loss": 0.8643, "step": 209 }, { "epoch": 0.36617262423714037, "grad_norm": 0.8922176361083984, "learning_rate": 8.811881188118812e-05, "loss": 0.8756, "step": 210 }, { "epoch": 0.3679163034001744, "grad_norm": 0.6775667071342468, "learning_rate": 8.806057076295865e-05, "loss": 0.7498, "step": 211 }, { "epoch": 0.36965998256320837, "grad_norm": 0.8060852289199829, "learning_rate": 8.800232964472919e-05, "loss": 0.8528, "step": 212 }, { "epoch": 0.3714036617262424, "grad_norm": 0.8279241919517517, "learning_rate": 8.794408852649971e-05, "loss": 0.9523, "step": 213 }, { "epoch": 0.37314734088927637, "grad_norm": 0.8296208381652832, "learning_rate": 8.788584740827024e-05, "loss": 0.8357, "step": 214 }, { "epoch": 0.3748910200523104, "grad_norm": 1.02497398853302, "learning_rate": 8.782760629004078e-05, "loss": 0.9002, "step": 215 }, { "epoch": 0.37663469921534437, "grad_norm": 0.7983161211013794, "learning_rate": 8.776936517181131e-05, "loss": 0.8479, "step": 216 }, { "epoch": 0.3783783783783784, "grad_norm": 0.7442088723182678, "learning_rate": 8.771112405358183e-05, "loss": 0.8401, "step": 217 }, { "epoch": 0.3801220575414124, "grad_norm": 0.7717306017875671, "learning_rate": 8.765288293535236e-05, "loss": 0.8401, "step": 218 }, { "epoch": 0.3818657367044464, "grad_norm": 0.924358606338501, "learning_rate": 8.759464181712289e-05, "loss": 0.907, "step": 219 }, { "epoch": 0.3836094158674804, "grad_norm": 0.7892866134643555, "learning_rate": 8.753640069889343e-05, "loss": 0.8514, "step": 220 }, { "epoch": 0.3853530950305144, "grad_norm": 0.637240469455719, "learning_rate": 8.747815958066396e-05, "loss": 0.769, "step": 221 }, { "epoch": 0.3870967741935484, "grad_norm": 1.0173636674880981, "learning_rate": 8.741991846243448e-05, "loss": 0.9416, "step": 222 }, { "epoch": 0.3888404533565824, "grad_norm": 0.7439960837364197, "learning_rate": 8.736167734420502e-05, "loss": 0.8519, "step": 223 }, { "epoch": 0.3905841325196164, "grad_norm": 0.8098750114440918, "learning_rate": 8.730343622597555e-05, "loss": 0.8446, "step": 224 }, { "epoch": 0.3923278116826504, "grad_norm": 0.8228147625923157, "learning_rate": 8.724519510774606e-05, "loss": 0.9199, "step": 225 }, { "epoch": 0.3940714908456844, "grad_norm": 0.6745813488960266, "learning_rate": 8.71869539895166e-05, "loss": 0.8008, "step": 226 }, { "epoch": 0.3958151700087184, "grad_norm": 0.8307877779006958, "learning_rate": 8.712871287128713e-05, "loss": 0.9322, "step": 227 }, { "epoch": 0.3975588491717524, "grad_norm": 0.7651572227478027, "learning_rate": 8.707047175305766e-05, "loss": 0.7856, "step": 228 }, { "epoch": 0.3993025283347864, "grad_norm": 0.8977913856506348, "learning_rate": 8.70122306348282e-05, "loss": 0.8906, "step": 229 }, { "epoch": 0.4010462074978204, "grad_norm": 0.8149082064628601, "learning_rate": 8.695398951659872e-05, "loss": 0.869, "step": 230 }, { "epoch": 0.4027898866608544, "grad_norm": 0.722152590751648, "learning_rate": 8.689574839836925e-05, "loss": 0.8096, "step": 231 }, { "epoch": 0.4045335658238884, "grad_norm": 0.910441517829895, "learning_rate": 8.683750728013978e-05, "loss": 0.8794, "step": 232 }, { "epoch": 0.4062772449869224, "grad_norm": 0.8773559331893921, "learning_rate": 8.67792661619103e-05, "loss": 0.8332, "step": 233 }, { "epoch": 0.4080209241499564, "grad_norm": 0.7504658102989197, "learning_rate": 8.672102504368085e-05, "loss": 0.8305, "step": 234 }, { "epoch": 0.4097646033129904, "grad_norm": 0.8077071905136108, "learning_rate": 8.666278392545137e-05, "loss": 0.9015, "step": 235 }, { "epoch": 0.4115082824760244, "grad_norm": 0.7554852366447449, "learning_rate": 8.66045428072219e-05, "loss": 0.8426, "step": 236 }, { "epoch": 0.4132519616390584, "grad_norm": 0.8291925191879272, "learning_rate": 8.654630168899244e-05, "loss": 0.8308, "step": 237 }, { "epoch": 0.4149956408020924, "grad_norm": 0.9522584080696106, "learning_rate": 8.648806057076297e-05, "loss": 0.8999, "step": 238 }, { "epoch": 0.4167393199651264, "grad_norm": 0.9483405947685242, "learning_rate": 8.64298194525335e-05, "loss": 0.821, "step": 239 }, { "epoch": 0.4184829991281604, "grad_norm": 0.6401641368865967, "learning_rate": 8.637157833430402e-05, "loss": 0.7948, "step": 240 }, { "epoch": 0.4202266782911944, "grad_norm": 0.8424367308616638, "learning_rate": 8.631333721607455e-05, "loss": 0.821, "step": 241 }, { "epoch": 0.4219703574542284, "grad_norm": 0.8348891139030457, "learning_rate": 8.625509609784507e-05, "loss": 0.9849, "step": 242 }, { "epoch": 0.4237140366172624, "grad_norm": 1.1707719564437866, "learning_rate": 8.619685497961562e-05, "loss": 1.0007, "step": 243 }, { "epoch": 0.42545771578029645, "grad_norm": 0.7723183631896973, "learning_rate": 8.613861386138614e-05, "loss": 0.8433, "step": 244 }, { "epoch": 0.4272013949433304, "grad_norm": 0.8192483186721802, "learning_rate": 8.608037274315667e-05, "loss": 0.854, "step": 245 }, { "epoch": 0.42894507410636445, "grad_norm": 0.830136239528656, "learning_rate": 8.602213162492721e-05, "loss": 0.8967, "step": 246 }, { "epoch": 0.4306887532693984, "grad_norm": 0.7540462613105774, "learning_rate": 8.596389050669774e-05, "loss": 0.7886, "step": 247 }, { "epoch": 0.43243243243243246, "grad_norm": 1.1086032390594482, "learning_rate": 8.590564938846826e-05, "loss": 0.9773, "step": 248 }, { "epoch": 0.43417611159546643, "grad_norm": 0.8502962589263916, "learning_rate": 8.584740827023879e-05, "loss": 0.8437, "step": 249 }, { "epoch": 0.43591979075850046, "grad_norm": 0.8264390826225281, "learning_rate": 8.578916715200932e-05, "loss": 0.8709, "step": 250 }, { "epoch": 0.43766346992153443, "grad_norm": 0.9108510613441467, "learning_rate": 8.573092603377986e-05, "loss": 0.8099, "step": 251 }, { "epoch": 0.43940714908456846, "grad_norm": 1.0819939374923706, "learning_rate": 8.567268491555038e-05, "loss": 0.9593, "step": 252 }, { "epoch": 0.44115082824760243, "grad_norm": 0.7228825688362122, "learning_rate": 8.561444379732091e-05, "loss": 0.8307, "step": 253 }, { "epoch": 0.44289450741063646, "grad_norm": 0.7428597211837769, "learning_rate": 8.555620267909145e-05, "loss": 0.7461, "step": 254 }, { "epoch": 0.44463818657367044, "grad_norm": 0.6365272402763367, "learning_rate": 8.549796156086198e-05, "loss": 0.8236, "step": 255 }, { "epoch": 0.44638186573670446, "grad_norm": 0.7026289105415344, "learning_rate": 8.543972044263249e-05, "loss": 0.8194, "step": 256 }, { "epoch": 0.44812554489973844, "grad_norm": 0.7578291893005371, "learning_rate": 8.538147932440303e-05, "loss": 0.7708, "step": 257 }, { "epoch": 0.44986922406277247, "grad_norm": 0.6669835448265076, "learning_rate": 8.532323820617356e-05, "loss": 0.7571, "step": 258 }, { "epoch": 0.45161290322580644, "grad_norm": 0.7768597602844238, "learning_rate": 8.526499708794409e-05, "loss": 0.867, "step": 259 }, { "epoch": 0.45335658238884047, "grad_norm": 1.0901800394058228, "learning_rate": 8.520675596971463e-05, "loss": 0.849, "step": 260 }, { "epoch": 0.45510026155187444, "grad_norm": 0.7377331852912903, "learning_rate": 8.514851485148515e-05, "loss": 0.7736, "step": 261 }, { "epoch": 0.45684394071490847, "grad_norm": 1.0414115190505981, "learning_rate": 8.50902737332557e-05, "loss": 0.9628, "step": 262 }, { "epoch": 0.45858761987794244, "grad_norm": 0.9939663410186768, "learning_rate": 8.503203261502621e-05, "loss": 0.9256, "step": 263 }, { "epoch": 0.46033129904097647, "grad_norm": 0.9058008193969727, "learning_rate": 8.497379149679673e-05, "loss": 0.8377, "step": 264 }, { "epoch": 0.46207497820401044, "grad_norm": 0.9659683108329773, "learning_rate": 8.491555037856727e-05, "loss": 0.9806, "step": 265 }, { "epoch": 0.4638186573670445, "grad_norm": 0.9084481000900269, "learning_rate": 8.48573092603378e-05, "loss": 0.8071, "step": 266 }, { "epoch": 0.46556233653007845, "grad_norm": 0.9308486580848694, "learning_rate": 8.479906814210833e-05, "loss": 0.8332, "step": 267 }, { "epoch": 0.4673060156931125, "grad_norm": 0.8791357278823853, "learning_rate": 8.474082702387887e-05, "loss": 0.7921, "step": 268 }, { "epoch": 0.46904969485614645, "grad_norm": 0.8986927270889282, "learning_rate": 8.46825859056494e-05, "loss": 0.9136, "step": 269 }, { "epoch": 0.4707933740191805, "grad_norm": 1.0948989391326904, "learning_rate": 8.462434478741992e-05, "loss": 0.9884, "step": 270 }, { "epoch": 0.47253705318221445, "grad_norm": 0.7958832383155823, "learning_rate": 8.456610366919045e-05, "loss": 0.8023, "step": 271 }, { "epoch": 0.4742807323452485, "grad_norm": 0.6921520233154297, "learning_rate": 8.450786255096098e-05, "loss": 0.8104, "step": 272 }, { "epoch": 0.47602441150828245, "grad_norm": 0.8654911518096924, "learning_rate": 8.44496214327315e-05, "loss": 0.9353, "step": 273 }, { "epoch": 0.4777680906713165, "grad_norm": 0.7776755094528198, "learning_rate": 8.439138031450204e-05, "loss": 0.845, "step": 274 }, { "epoch": 0.47951176983435045, "grad_norm": 0.8736585974693298, "learning_rate": 8.433313919627257e-05, "loss": 0.89, "step": 275 }, { "epoch": 0.4812554489973845, "grad_norm": 0.7322900891304016, "learning_rate": 8.427489807804311e-05, "loss": 0.8055, "step": 276 }, { "epoch": 0.48299912816041846, "grad_norm": 0.710942804813385, "learning_rate": 8.421665695981364e-05, "loss": 0.8691, "step": 277 }, { "epoch": 0.4847428073234525, "grad_norm": 0.8033804297447205, "learning_rate": 8.415841584158417e-05, "loss": 0.8425, "step": 278 }, { "epoch": 0.4864864864864865, "grad_norm": 0.7597092390060425, "learning_rate": 8.410017472335469e-05, "loss": 0.8404, "step": 279 }, { "epoch": 0.4882301656495205, "grad_norm": 0.7505855560302734, "learning_rate": 8.404193360512522e-05, "loss": 0.8278, "step": 280 }, { "epoch": 0.4899738448125545, "grad_norm": 0.9316595196723938, "learning_rate": 8.398369248689575e-05, "loss": 0.9489, "step": 281 }, { "epoch": 0.4917175239755885, "grad_norm": 1.1016560792922974, "learning_rate": 8.392545136866629e-05, "loss": 1.0027, "step": 282 }, { "epoch": 0.4934612031386225, "grad_norm": 0.6287282705307007, "learning_rate": 8.386721025043681e-05, "loss": 0.7788, "step": 283 }, { "epoch": 0.4952048823016565, "grad_norm": 0.8679805397987366, "learning_rate": 8.380896913220734e-05, "loss": 0.8963, "step": 284 }, { "epoch": 0.4969485614646905, "grad_norm": 0.7580657005310059, "learning_rate": 8.375072801397788e-05, "loss": 0.8096, "step": 285 }, { "epoch": 0.4986922406277245, "grad_norm": 0.7760534882545471, "learning_rate": 8.36924868957484e-05, "loss": 0.9031, "step": 286 }, { "epoch": 0.5004359197907585, "grad_norm": 0.9266983270645142, "learning_rate": 8.363424577751892e-05, "loss": 0.9279, "step": 287 }, { "epoch": 0.5021795989537925, "grad_norm": 1.004073977470398, "learning_rate": 8.357600465928946e-05, "loss": 0.9447, "step": 288 }, { "epoch": 0.5039232781168265, "grad_norm": 0.8203737139701843, "learning_rate": 8.351776354105999e-05, "loss": 0.7876, "step": 289 }, { "epoch": 0.5056669572798606, "grad_norm": 0.7546892762184143, "learning_rate": 8.345952242283053e-05, "loss": 0.8943, "step": 290 }, { "epoch": 0.5074106364428945, "grad_norm": 0.9076023697853088, "learning_rate": 8.340128130460106e-05, "loss": 0.925, "step": 291 }, { "epoch": 0.5091543156059285, "grad_norm": 0.8324609398841858, "learning_rate": 8.334304018637158e-05, "loss": 0.9693, "step": 292 }, { "epoch": 0.5108979947689625, "grad_norm": 0.7717570662498474, "learning_rate": 8.328479906814211e-05, "loss": 0.8337, "step": 293 }, { "epoch": 0.5126416739319966, "grad_norm": 0.6931645274162292, "learning_rate": 8.322655794991264e-05, "loss": 0.8273, "step": 294 }, { "epoch": 0.5143853530950305, "grad_norm": 0.9506610035896301, "learning_rate": 8.316831683168316e-05, "loss": 0.8787, "step": 295 }, { "epoch": 0.5161290322580645, "grad_norm": 1.000448226928711, "learning_rate": 8.31100757134537e-05, "loss": 0.9923, "step": 296 }, { "epoch": 0.5178727114210985, "grad_norm": 0.6892333626747131, "learning_rate": 8.305183459522423e-05, "loss": 0.7218, "step": 297 }, { "epoch": 0.5196163905841326, "grad_norm": 0.7098091840744019, "learning_rate": 8.299359347699476e-05, "loss": 0.7398, "step": 298 }, { "epoch": 0.5213600697471665, "grad_norm": 0.8102613687515259, "learning_rate": 8.29353523587653e-05, "loss": 0.8499, "step": 299 }, { "epoch": 0.5231037489102005, "grad_norm": 0.9031519889831543, "learning_rate": 8.287711124053583e-05, "loss": 0.9237, "step": 300 }, { "epoch": 0.5248474280732345, "grad_norm": 0.8423986434936523, "learning_rate": 8.281887012230635e-05, "loss": 0.9013, "step": 301 }, { "epoch": 0.5265911072362686, "grad_norm": 0.8308762311935425, "learning_rate": 8.276062900407688e-05, "loss": 0.8205, "step": 302 }, { "epoch": 0.5283347863993025, "grad_norm": 1.0304760932922363, "learning_rate": 8.27023878858474e-05, "loss": 0.9311, "step": 303 }, { "epoch": 0.5300784655623365, "grad_norm": 0.8758693337440491, "learning_rate": 8.264414676761795e-05, "loss": 0.8489, "step": 304 }, { "epoch": 0.5318221447253705, "grad_norm": 0.8235571980476379, "learning_rate": 8.258590564938847e-05, "loss": 0.828, "step": 305 }, { "epoch": 0.5335658238884046, "grad_norm": 0.7034077048301697, "learning_rate": 8.2527664531159e-05, "loss": 0.7403, "step": 306 }, { "epoch": 0.5353095030514385, "grad_norm": 0.8910762667655945, "learning_rate": 8.246942341292954e-05, "loss": 0.8847, "step": 307 }, { "epoch": 0.5370531822144725, "grad_norm": 0.9173892140388489, "learning_rate": 8.241118229470007e-05, "loss": 0.9131, "step": 308 }, { "epoch": 0.5387968613775065, "grad_norm": 0.799484133720398, "learning_rate": 8.23529411764706e-05, "loss": 0.8599, "step": 309 }, { "epoch": 0.5405405405405406, "grad_norm": 0.7972217798233032, "learning_rate": 8.229470005824112e-05, "loss": 0.8024, "step": 310 }, { "epoch": 0.5422842197035745, "grad_norm": 0.7904372215270996, "learning_rate": 8.223645894001165e-05, "loss": 0.8708, "step": 311 }, { "epoch": 0.5440278988666085, "grad_norm": 0.7752811908721924, "learning_rate": 8.217821782178218e-05, "loss": 0.8695, "step": 312 }, { "epoch": 0.5457715780296426, "grad_norm": 0.6934289336204529, "learning_rate": 8.211997670355272e-05, "loss": 0.7912, "step": 313 }, { "epoch": 0.5475152571926766, "grad_norm": 1.0247608423233032, "learning_rate": 8.206173558532324e-05, "loss": 0.9333, "step": 314 }, { "epoch": 0.5492589363557105, "grad_norm": 0.7217332720756531, "learning_rate": 8.200349446709377e-05, "loss": 0.8579, "step": 315 }, { "epoch": 0.5510026155187445, "grad_norm": 0.8623534440994263, "learning_rate": 8.194525334886431e-05, "loss": 0.8563, "step": 316 }, { "epoch": 0.5527462946817786, "grad_norm": 0.9250230193138123, "learning_rate": 8.188701223063482e-05, "loss": 0.9132, "step": 317 }, { "epoch": 0.5544899738448126, "grad_norm": 0.8964390754699707, "learning_rate": 8.182877111240536e-05, "loss": 0.8865, "step": 318 }, { "epoch": 0.5562336530078466, "grad_norm": 0.7463217973709106, "learning_rate": 8.177052999417589e-05, "loss": 0.8486, "step": 319 }, { "epoch": 0.5579773321708805, "grad_norm": 0.7544821500778198, "learning_rate": 8.171228887594642e-05, "loss": 0.8219, "step": 320 }, { "epoch": 0.5597210113339146, "grad_norm": 0.7603556513786316, "learning_rate": 8.165404775771696e-05, "loss": 0.932, "step": 321 }, { "epoch": 0.5614646904969486, "grad_norm": 0.8567686676979065, "learning_rate": 8.159580663948749e-05, "loss": 0.7978, "step": 322 }, { "epoch": 0.5632083696599826, "grad_norm": 1.165769338607788, "learning_rate": 8.153756552125801e-05, "loss": 0.9775, "step": 323 }, { "epoch": 0.5649520488230165, "grad_norm": 0.7291504144668579, "learning_rate": 8.147932440302854e-05, "loss": 0.778, "step": 324 }, { "epoch": 0.5666957279860506, "grad_norm": 0.7615162134170532, "learning_rate": 8.142108328479907e-05, "loss": 0.7787, "step": 325 }, { "epoch": 0.5684394071490846, "grad_norm": 1.0282222032546997, "learning_rate": 8.136284216656959e-05, "loss": 0.9892, "step": 326 }, { "epoch": 0.5701830863121186, "grad_norm": 0.7557792663574219, "learning_rate": 8.130460104834013e-05, "loss": 0.8287, "step": 327 }, { "epoch": 0.5719267654751525, "grad_norm": 0.83980792760849, "learning_rate": 8.124635993011066e-05, "loss": 0.8623, "step": 328 }, { "epoch": 0.5736704446381866, "grad_norm": 0.934972882270813, "learning_rate": 8.11881188118812e-05, "loss": 0.8714, "step": 329 }, { "epoch": 0.5754141238012206, "grad_norm": 0.7756255269050598, "learning_rate": 8.112987769365173e-05, "loss": 0.8725, "step": 330 }, { "epoch": 0.5771578029642546, "grad_norm": 0.742637038230896, "learning_rate": 8.107163657542225e-05, "loss": 0.859, "step": 331 }, { "epoch": 0.5789014821272885, "grad_norm": 0.8098328113555908, "learning_rate": 8.101339545719278e-05, "loss": 0.8959, "step": 332 }, { "epoch": 0.5806451612903226, "grad_norm": 0.7302229404449463, "learning_rate": 8.095515433896331e-05, "loss": 0.7741, "step": 333 }, { "epoch": 0.5823888404533566, "grad_norm": 0.8232591152191162, "learning_rate": 8.089691322073384e-05, "loss": 0.9411, "step": 334 }, { "epoch": 0.5841325196163906, "grad_norm": 0.7742142081260681, "learning_rate": 8.083867210250438e-05, "loss": 0.8133, "step": 335 }, { "epoch": 0.5858761987794245, "grad_norm": 0.8862509727478027, "learning_rate": 8.07804309842749e-05, "loss": 0.8933, "step": 336 }, { "epoch": 0.5876198779424586, "grad_norm": 0.6707773208618164, "learning_rate": 8.072218986604543e-05, "loss": 0.8362, "step": 337 }, { "epoch": 0.5893635571054926, "grad_norm": 0.8191516399383545, "learning_rate": 8.066394874781597e-05, "loss": 0.7993, "step": 338 }, { "epoch": 0.5911072362685266, "grad_norm": 0.8699632287025452, "learning_rate": 8.06057076295865e-05, "loss": 0.8491, "step": 339 }, { "epoch": 0.5928509154315605, "grad_norm": 0.7079885601997375, "learning_rate": 8.054746651135702e-05, "loss": 0.7863, "step": 340 }, { "epoch": 0.5945945945945946, "grad_norm": 1.0028823614120483, "learning_rate": 8.048922539312755e-05, "loss": 0.9232, "step": 341 }, { "epoch": 0.5963382737576286, "grad_norm": 0.7121110558509827, "learning_rate": 8.043098427489808e-05, "loss": 0.7749, "step": 342 }, { "epoch": 0.5980819529206626, "grad_norm": 0.9713465571403503, "learning_rate": 8.037274315666862e-05, "loss": 0.8034, "step": 343 }, { "epoch": 0.5998256320836965, "grad_norm": 1.013658881187439, "learning_rate": 8.031450203843914e-05, "loss": 0.9412, "step": 344 }, { "epoch": 0.6015693112467306, "grad_norm": 0.8425729274749756, "learning_rate": 8.025626092020967e-05, "loss": 0.8519, "step": 345 }, { "epoch": 0.6033129904097646, "grad_norm": 0.7781736850738525, "learning_rate": 8.019801980198021e-05, "loss": 0.8721, "step": 346 }, { "epoch": 0.6050566695727986, "grad_norm": 0.8602432012557983, "learning_rate": 8.013977868375074e-05, "loss": 0.9023, "step": 347 }, { "epoch": 0.6068003487358327, "grad_norm": 0.7517696022987366, "learning_rate": 8.008153756552125e-05, "loss": 0.7825, "step": 348 }, { "epoch": 0.6085440278988666, "grad_norm": 0.7462587952613831, "learning_rate": 8.002329644729179e-05, "loss": 0.9261, "step": 349 }, { "epoch": 0.6102877070619006, "grad_norm": 0.7866942882537842, "learning_rate": 7.996505532906232e-05, "loss": 0.9169, "step": 350 }, { "epoch": 0.6120313862249346, "grad_norm": 0.6872032284736633, "learning_rate": 7.990681421083285e-05, "loss": 0.834, "step": 351 }, { "epoch": 0.6137750653879687, "grad_norm": 0.7469502091407776, "learning_rate": 7.984857309260339e-05, "loss": 0.8586, "step": 352 }, { "epoch": 0.6155187445510026, "grad_norm": 0.8394846320152283, "learning_rate": 7.979033197437391e-05, "loss": 0.8026, "step": 353 }, { "epoch": 0.6172624237140366, "grad_norm": 0.7591722011566162, "learning_rate": 7.973209085614444e-05, "loss": 0.8598, "step": 354 }, { "epoch": 0.6190061028770706, "grad_norm": 0.8345113396644592, "learning_rate": 7.967384973791497e-05, "loss": 0.858, "step": 355 }, { "epoch": 0.6207497820401047, "grad_norm": 0.8436324000358582, "learning_rate": 7.96156086196855e-05, "loss": 0.8774, "step": 356 }, { "epoch": 0.6224934612031386, "grad_norm": 0.8483322262763977, "learning_rate": 7.955736750145604e-05, "loss": 0.8311, "step": 357 }, { "epoch": 0.6242371403661726, "grad_norm": 0.7489394545555115, "learning_rate": 7.949912638322656e-05, "loss": 0.7684, "step": 358 }, { "epoch": 0.6259808195292066, "grad_norm": 0.6670379638671875, "learning_rate": 7.944088526499709e-05, "loss": 0.8266, "step": 359 }, { "epoch": 0.6277244986922407, "grad_norm": 0.8161701560020447, "learning_rate": 7.938264414676763e-05, "loss": 0.878, "step": 360 }, { "epoch": 0.6294681778552746, "grad_norm": 0.749869704246521, "learning_rate": 7.932440302853816e-05, "loss": 0.8626, "step": 361 }, { "epoch": 0.6312118570183086, "grad_norm": 0.7530505657196045, "learning_rate": 7.926616191030868e-05, "loss": 0.8229, "step": 362 }, { "epoch": 0.6329555361813426, "grad_norm": 1.3500347137451172, "learning_rate": 7.920792079207921e-05, "loss": 1.0724, "step": 363 }, { "epoch": 0.6346992153443767, "grad_norm": 0.7080022692680359, "learning_rate": 7.914967967384974e-05, "loss": 0.8183, "step": 364 }, { "epoch": 0.6364428945074107, "grad_norm": 0.9698605537414551, "learning_rate": 7.909143855562026e-05, "loss": 0.8393, "step": 365 }, { "epoch": 0.6381865736704446, "grad_norm": 0.9232154488563538, "learning_rate": 7.90331974373908e-05, "loss": 0.9123, "step": 366 }, { "epoch": 0.6399302528334786, "grad_norm": 1.0399445295333862, "learning_rate": 7.897495631916133e-05, "loss": 0.9716, "step": 367 }, { "epoch": 0.6416739319965127, "grad_norm": 0.6555128693580627, "learning_rate": 7.891671520093186e-05, "loss": 0.7896, "step": 368 }, { "epoch": 0.6434176111595467, "grad_norm": 0.9301493167877197, "learning_rate": 7.88584740827024e-05, "loss": 0.8527, "step": 369 }, { "epoch": 0.6451612903225806, "grad_norm": 0.7681971788406372, "learning_rate": 7.880023296447293e-05, "loss": 0.8259, "step": 370 }, { "epoch": 0.6469049694856146, "grad_norm": 0.8389270305633545, "learning_rate": 7.874199184624345e-05, "loss": 0.8584, "step": 371 }, { "epoch": 0.6486486486486487, "grad_norm": 0.9380039572715759, "learning_rate": 7.868375072801398e-05, "loss": 0.9089, "step": 372 }, { "epoch": 0.6503923278116827, "grad_norm": 0.6769824028015137, "learning_rate": 7.86255096097845e-05, "loss": 0.7719, "step": 373 }, { "epoch": 0.6521360069747166, "grad_norm": 0.7858641743659973, "learning_rate": 7.856726849155505e-05, "loss": 0.8096, "step": 374 }, { "epoch": 0.6538796861377506, "grad_norm": 1.0454126596450806, "learning_rate": 7.850902737332557e-05, "loss": 0.8697, "step": 375 }, { "epoch": 0.6556233653007847, "grad_norm": 1.3261022567749023, "learning_rate": 7.84507862550961e-05, "loss": 1.0573, "step": 376 }, { "epoch": 0.6573670444638187, "grad_norm": 0.9173828959465027, "learning_rate": 7.839254513686664e-05, "loss": 0.9247, "step": 377 }, { "epoch": 0.6591107236268526, "grad_norm": 0.8878739476203918, "learning_rate": 7.833430401863715e-05, "loss": 0.845, "step": 378 }, { "epoch": 0.6608544027898866, "grad_norm": 0.7334930300712585, "learning_rate": 7.827606290040768e-05, "loss": 0.8415, "step": 379 }, { "epoch": 0.6625980819529207, "grad_norm": 0.8551143407821655, "learning_rate": 7.821782178217822e-05, "loss": 0.8093, "step": 380 }, { "epoch": 0.6643417611159547, "grad_norm": 0.7278879880905151, "learning_rate": 7.815958066394875e-05, "loss": 0.7471, "step": 381 }, { "epoch": 0.6660854402789886, "grad_norm": 1.0607495307922363, "learning_rate": 7.810133954571928e-05, "loss": 0.9746, "step": 382 }, { "epoch": 0.6678291194420227, "grad_norm": 0.7543691992759705, "learning_rate": 7.804309842748982e-05, "loss": 0.8331, "step": 383 }, { "epoch": 0.6695727986050567, "grad_norm": 0.735906720161438, "learning_rate": 7.798485730926034e-05, "loss": 0.7933, "step": 384 }, { "epoch": 0.6713164777680907, "grad_norm": 0.6626788973808289, "learning_rate": 7.792661619103087e-05, "loss": 0.8242, "step": 385 }, { "epoch": 0.6730601569311246, "grad_norm": 0.8222870826721191, "learning_rate": 7.78683750728014e-05, "loss": 0.8617, "step": 386 }, { "epoch": 0.6748038360941587, "grad_norm": 0.9679776430130005, "learning_rate": 7.781013395457192e-05, "loss": 0.8986, "step": 387 }, { "epoch": 0.6765475152571927, "grad_norm": 0.7322062849998474, "learning_rate": 7.775189283634246e-05, "loss": 0.8726, "step": 388 }, { "epoch": 0.6782911944202267, "grad_norm": 0.7300450801849365, "learning_rate": 7.769365171811299e-05, "loss": 0.7981, "step": 389 }, { "epoch": 0.6800348735832606, "grad_norm": 0.8295143246650696, "learning_rate": 7.763541059988352e-05, "loss": 0.9362, "step": 390 }, { "epoch": 0.6817785527462947, "grad_norm": 0.7706050276756287, "learning_rate": 7.757716948165406e-05, "loss": 0.9169, "step": 391 }, { "epoch": 0.6835222319093287, "grad_norm": 0.7877134084701538, "learning_rate": 7.751892836342459e-05, "loss": 0.8261, "step": 392 }, { "epoch": 0.6852659110723627, "grad_norm": 0.8892063498497009, "learning_rate": 7.746068724519511e-05, "loss": 0.8089, "step": 393 }, { "epoch": 0.6870095902353966, "grad_norm": 0.9344806671142578, "learning_rate": 7.740244612696564e-05, "loss": 0.9706, "step": 394 }, { "epoch": 0.6887532693984307, "grad_norm": 0.8563032746315002, "learning_rate": 7.734420500873617e-05, "loss": 0.9047, "step": 395 }, { "epoch": 0.6904969485614647, "grad_norm": 0.7258780598640442, "learning_rate": 7.72859638905067e-05, "loss": 0.8041, "step": 396 }, { "epoch": 0.6922406277244987, "grad_norm": 0.8554896116256714, "learning_rate": 7.722772277227723e-05, "loss": 0.8873, "step": 397 }, { "epoch": 0.6939843068875327, "grad_norm": 0.709589958190918, "learning_rate": 7.716948165404776e-05, "loss": 0.8343, "step": 398 }, { "epoch": 0.6957279860505667, "grad_norm": 0.7512774467468262, "learning_rate": 7.71112405358183e-05, "loss": 0.8351, "step": 399 }, { "epoch": 0.6974716652136007, "grad_norm": 0.7866894006729126, "learning_rate": 7.705299941758883e-05, "loss": 0.8383, "step": 400 }, { "epoch": 0.6992153443766347, "grad_norm": 0.6562144756317139, "learning_rate": 7.699475829935936e-05, "loss": 0.8239, "step": 401 }, { "epoch": 0.7009590235396687, "grad_norm": 0.8547206521034241, "learning_rate": 7.693651718112988e-05, "loss": 0.8684, "step": 402 }, { "epoch": 0.7027027027027027, "grad_norm": 0.8460413813591003, "learning_rate": 7.687827606290041e-05, "loss": 0.8863, "step": 403 }, { "epoch": 0.7044463818657367, "grad_norm": 0.8831700682640076, "learning_rate": 7.682003494467094e-05, "loss": 0.9017, "step": 404 }, { "epoch": 0.7061900610287707, "grad_norm": 0.8952875137329102, "learning_rate": 7.676179382644148e-05, "loss": 0.8197, "step": 405 }, { "epoch": 0.7079337401918047, "grad_norm": 0.7152301073074341, "learning_rate": 7.6703552708212e-05, "loss": 0.8225, "step": 406 }, { "epoch": 0.7096774193548387, "grad_norm": 0.6562944650650024, "learning_rate": 7.664531158998253e-05, "loss": 0.7713, "step": 407 }, { "epoch": 0.7114210985178727, "grad_norm": 0.7383171916007996, "learning_rate": 7.658707047175307e-05, "loss": 0.833, "step": 408 }, { "epoch": 0.7131647776809067, "grad_norm": 0.7290094494819641, "learning_rate": 7.652882935352358e-05, "loss": 0.8678, "step": 409 }, { "epoch": 0.7149084568439407, "grad_norm": 0.7877590656280518, "learning_rate": 7.647058823529411e-05, "loss": 0.7999, "step": 410 }, { "epoch": 0.7166521360069747, "grad_norm": 0.7994208931922913, "learning_rate": 7.641234711706465e-05, "loss": 0.7635, "step": 411 }, { "epoch": 0.7183958151700087, "grad_norm": 0.7631087899208069, "learning_rate": 7.635410599883518e-05, "loss": 0.8096, "step": 412 }, { "epoch": 0.7201394943330427, "grad_norm": 0.951224148273468, "learning_rate": 7.629586488060572e-05, "loss": 0.9389, "step": 413 }, { "epoch": 0.7218831734960767, "grad_norm": 0.8487862944602966, "learning_rate": 7.623762376237625e-05, "loss": 0.8077, "step": 414 }, { "epoch": 0.7236268526591108, "grad_norm": 0.8798261880874634, "learning_rate": 7.617938264414677e-05, "loss": 0.7953, "step": 415 }, { "epoch": 0.7253705318221447, "grad_norm": 0.7842178344726562, "learning_rate": 7.61211415259173e-05, "loss": 0.7335, "step": 416 }, { "epoch": 0.7271142109851787, "grad_norm": 0.6394723057746887, "learning_rate": 7.606290040768783e-05, "loss": 0.6983, "step": 417 }, { "epoch": 0.7288578901482128, "grad_norm": 1.0838403701782227, "learning_rate": 7.600465928945835e-05, "loss": 0.8543, "step": 418 }, { "epoch": 0.7306015693112468, "grad_norm": 0.7571240663528442, "learning_rate": 7.59464181712289e-05, "loss": 0.8752, "step": 419 }, { "epoch": 0.7323452484742807, "grad_norm": 0.7818177938461304, "learning_rate": 7.588817705299942e-05, "loss": 0.8053, "step": 420 }, { "epoch": 0.7340889276373147, "grad_norm": 0.9264829754829407, "learning_rate": 7.582993593476995e-05, "loss": 0.9503, "step": 421 }, { "epoch": 0.7358326068003488, "grad_norm": 0.7863692045211792, "learning_rate": 7.577169481654049e-05, "loss": 0.8611, "step": 422 }, { "epoch": 0.7375762859633828, "grad_norm": 0.8430398106575012, "learning_rate": 7.571345369831102e-05, "loss": 0.8802, "step": 423 }, { "epoch": 0.7393199651264167, "grad_norm": 0.7615321278572083, "learning_rate": 7.565521258008154e-05, "loss": 0.8632, "step": 424 }, { "epoch": 0.7410636442894507, "grad_norm": 0.8452615737915039, "learning_rate": 7.559697146185207e-05, "loss": 0.8838, "step": 425 }, { "epoch": 0.7428073234524848, "grad_norm": 0.809556782245636, "learning_rate": 7.55387303436226e-05, "loss": 0.8787, "step": 426 }, { "epoch": 0.7445510026155188, "grad_norm": 0.8575369715690613, "learning_rate": 7.548048922539314e-05, "loss": 0.8902, "step": 427 }, { "epoch": 0.7462946817785527, "grad_norm": 0.7769126892089844, "learning_rate": 7.542224810716366e-05, "loss": 0.8693, "step": 428 }, { "epoch": 0.7480383609415867, "grad_norm": 0.8244854211807251, "learning_rate": 7.536400698893419e-05, "loss": 0.881, "step": 429 }, { "epoch": 0.7497820401046208, "grad_norm": 0.8230065107345581, "learning_rate": 7.530576587070473e-05, "loss": 0.839, "step": 430 }, { "epoch": 0.7515257192676548, "grad_norm": 0.8066556453704834, "learning_rate": 7.524752475247526e-05, "loss": 0.7425, "step": 431 }, { "epoch": 0.7532693984306887, "grad_norm": 0.8341608643531799, "learning_rate": 7.518928363424577e-05, "loss": 0.9174, "step": 432 }, { "epoch": 0.7550130775937227, "grad_norm": 0.8278172016143799, "learning_rate": 7.513104251601631e-05, "loss": 0.8431, "step": 433 }, { "epoch": 0.7567567567567568, "grad_norm": 0.6836431622505188, "learning_rate": 7.507280139778684e-05, "loss": 0.7374, "step": 434 }, { "epoch": 0.7585004359197908, "grad_norm": 0.8936211466789246, "learning_rate": 7.501456027955737e-05, "loss": 0.8602, "step": 435 }, { "epoch": 0.7602441150828247, "grad_norm": 0.8777217268943787, "learning_rate": 7.49563191613279e-05, "loss": 0.8719, "step": 436 }, { "epoch": 0.7619877942458587, "grad_norm": 0.9668258428573608, "learning_rate": 7.489807804309843e-05, "loss": 0.9357, "step": 437 }, { "epoch": 0.7637314734088928, "grad_norm": 0.7838490009307861, "learning_rate": 7.483983692486896e-05, "loss": 0.8752, "step": 438 }, { "epoch": 0.7654751525719268, "grad_norm": 0.7799532413482666, "learning_rate": 7.478159580663949e-05, "loss": 0.7505, "step": 439 }, { "epoch": 0.7672188317349607, "grad_norm": 0.9914664626121521, "learning_rate": 7.472335468841001e-05, "loss": 0.8371, "step": 440 }, { "epoch": 0.7689625108979947, "grad_norm": 0.7805373668670654, "learning_rate": 7.466511357018055e-05, "loss": 0.8148, "step": 441 }, { "epoch": 0.7707061900610288, "grad_norm": 0.9963315725326538, "learning_rate": 7.460687245195108e-05, "loss": 0.8374, "step": 442 }, { "epoch": 0.7724498692240628, "grad_norm": 0.8724879622459412, "learning_rate": 7.454863133372161e-05, "loss": 0.8938, "step": 443 }, { "epoch": 0.7741935483870968, "grad_norm": 0.7164104580879211, "learning_rate": 7.449039021549215e-05, "loss": 0.7543, "step": 444 }, { "epoch": 0.7759372275501307, "grad_norm": 1.1039303541183472, "learning_rate": 7.443214909726267e-05, "loss": 0.8746, "step": 445 }, { "epoch": 0.7776809067131648, "grad_norm": 1.0562795400619507, "learning_rate": 7.43739079790332e-05, "loss": 0.99, "step": 446 }, { "epoch": 0.7794245858761988, "grad_norm": 0.8625308275222778, "learning_rate": 7.431566686080373e-05, "loss": 0.8172, "step": 447 }, { "epoch": 0.7811682650392328, "grad_norm": 0.9858479499816895, "learning_rate": 7.425742574257426e-05, "loss": 0.9788, "step": 448 }, { "epoch": 0.7829119442022667, "grad_norm": 0.6775063276290894, "learning_rate": 7.419918462434478e-05, "loss": 0.7774, "step": 449 }, { "epoch": 0.7846556233653008, "grad_norm": 0.8109975457191467, "learning_rate": 7.414094350611532e-05, "loss": 0.7799, "step": 450 }, { "epoch": 0.7863993025283348, "grad_norm": 0.7447454929351807, "learning_rate": 7.408270238788585e-05, "loss": 0.7998, "step": 451 }, { "epoch": 0.7881429816913688, "grad_norm": 1.133470058441162, "learning_rate": 7.402446126965638e-05, "loss": 1.0, "step": 452 }, { "epoch": 0.7898866608544028, "grad_norm": 0.8419718146324158, "learning_rate": 7.396622015142692e-05, "loss": 0.8303, "step": 453 }, { "epoch": 0.7916303400174368, "grad_norm": 0.9642958641052246, "learning_rate": 7.390797903319744e-05, "loss": 0.943, "step": 454 }, { "epoch": 0.7933740191804708, "grad_norm": 0.7736382484436035, "learning_rate": 7.384973791496797e-05, "loss": 0.7733, "step": 455 }, { "epoch": 0.7951176983435048, "grad_norm": 0.6989179849624634, "learning_rate": 7.37914967967385e-05, "loss": 0.7733, "step": 456 }, { "epoch": 0.7968613775065388, "grad_norm": 0.8626717329025269, "learning_rate": 7.373325567850902e-05, "loss": 0.8239, "step": 457 }, { "epoch": 0.7986050566695728, "grad_norm": 0.8128955364227295, "learning_rate": 7.367501456027957e-05, "loss": 0.8237, "step": 458 }, { "epoch": 0.8003487358326068, "grad_norm": 0.8367345929145813, "learning_rate": 7.361677344205009e-05, "loss": 0.8576, "step": 459 }, { "epoch": 0.8020924149956408, "grad_norm": 0.9407440423965454, "learning_rate": 7.355853232382062e-05, "loss": 0.9516, "step": 460 }, { "epoch": 0.8038360941586749, "grad_norm": 0.7843737006187439, "learning_rate": 7.350029120559116e-05, "loss": 0.7879, "step": 461 }, { "epoch": 0.8055797733217088, "grad_norm": 0.7397564649581909, "learning_rate": 7.344205008736169e-05, "loss": 0.8231, "step": 462 }, { "epoch": 0.8073234524847428, "grad_norm": 1.0911139249801636, "learning_rate": 7.33838089691322e-05, "loss": 0.9567, "step": 463 }, { "epoch": 0.8090671316477768, "grad_norm": 1.0065691471099854, "learning_rate": 7.332556785090274e-05, "loss": 0.9079, "step": 464 }, { "epoch": 0.8108108108108109, "grad_norm": 0.6847046613693237, "learning_rate": 7.326732673267327e-05, "loss": 0.7904, "step": 465 }, { "epoch": 0.8125544899738448, "grad_norm": 0.7951462864875793, "learning_rate": 7.32090856144438e-05, "loss": 0.7874, "step": 466 }, { "epoch": 0.8142981691368788, "grad_norm": 0.7181991338729858, "learning_rate": 7.315084449621433e-05, "loss": 0.8264, "step": 467 }, { "epoch": 0.8160418482999128, "grad_norm": 0.9055427312850952, "learning_rate": 7.309260337798486e-05, "loss": 0.942, "step": 468 }, { "epoch": 0.8177855274629469, "grad_norm": 0.9564733505249023, "learning_rate": 7.30343622597554e-05, "loss": 0.8674, "step": 469 }, { "epoch": 0.8195292066259808, "grad_norm": 0.794967770576477, "learning_rate": 7.297612114152592e-05, "loss": 0.7854, "step": 470 }, { "epoch": 0.8212728857890148, "grad_norm": 0.6180671453475952, "learning_rate": 7.291788002329644e-05, "loss": 0.8104, "step": 471 }, { "epoch": 0.8230165649520488, "grad_norm": 0.9112799763679504, "learning_rate": 7.285963890506698e-05, "loss": 0.8589, "step": 472 }, { "epoch": 0.8247602441150829, "grad_norm": 0.9618897438049316, "learning_rate": 7.280139778683751e-05, "loss": 0.9346, "step": 473 }, { "epoch": 0.8265039232781168, "grad_norm": 0.8169216513633728, "learning_rate": 7.274315666860804e-05, "loss": 0.8652, "step": 474 }, { "epoch": 0.8282476024411508, "grad_norm": 0.8952524662017822, "learning_rate": 7.268491555037858e-05, "loss": 0.856, "step": 475 }, { "epoch": 0.8299912816041848, "grad_norm": 0.9359880089759827, "learning_rate": 7.26266744321491e-05, "loss": 0.8747, "step": 476 }, { "epoch": 0.8317349607672189, "grad_norm": 1.0236445665359497, "learning_rate": 7.256843331391963e-05, "loss": 1.0088, "step": 477 }, { "epoch": 0.8334786399302528, "grad_norm": 0.6680594682693481, "learning_rate": 7.251019219569016e-05, "loss": 0.7458, "step": 478 }, { "epoch": 0.8352223190932868, "grad_norm": 0.7986267805099487, "learning_rate": 7.245195107746068e-05, "loss": 0.799, "step": 479 }, { "epoch": 0.8369659982563208, "grad_norm": 0.8889102935791016, "learning_rate": 7.239370995923123e-05, "loss": 0.8715, "step": 480 }, { "epoch": 0.8387096774193549, "grad_norm": 0.9398014545440674, "learning_rate": 7.233546884100175e-05, "loss": 0.7977, "step": 481 }, { "epoch": 0.8404533565823888, "grad_norm": 1.020912528038025, "learning_rate": 7.227722772277228e-05, "loss": 0.7865, "step": 482 }, { "epoch": 0.8421970357454228, "grad_norm": 0.8154118657112122, "learning_rate": 7.221898660454282e-05, "loss": 0.8577, "step": 483 }, { "epoch": 0.8439407149084568, "grad_norm": 0.8049352765083313, "learning_rate": 7.216074548631335e-05, "loss": 0.8662, "step": 484 }, { "epoch": 0.8456843940714909, "grad_norm": 0.8422334790229797, "learning_rate": 7.210250436808387e-05, "loss": 0.8259, "step": 485 }, { "epoch": 0.8474280732345248, "grad_norm": 0.7848876714706421, "learning_rate": 7.20442632498544e-05, "loss": 0.8986, "step": 486 }, { "epoch": 0.8491717523975588, "grad_norm": 0.7896991968154907, "learning_rate": 7.198602213162493e-05, "loss": 0.8383, "step": 487 }, { "epoch": 0.8509154315605929, "grad_norm": 0.9751361012458801, "learning_rate": 7.192778101339545e-05, "loss": 0.828, "step": 488 }, { "epoch": 0.8526591107236269, "grad_norm": 0.6458632349967957, "learning_rate": 7.1869539895166e-05, "loss": 0.8201, "step": 489 }, { "epoch": 0.8544027898866609, "grad_norm": 0.71848464012146, "learning_rate": 7.181129877693652e-05, "loss": 0.8476, "step": 490 }, { "epoch": 0.8561464690496948, "grad_norm": 0.889597475528717, "learning_rate": 7.175305765870705e-05, "loss": 0.851, "step": 491 }, { "epoch": 0.8578901482127289, "grad_norm": 0.9084944128990173, "learning_rate": 7.169481654047759e-05, "loss": 0.8974, "step": 492 }, { "epoch": 0.8596338273757629, "grad_norm": 1.168218731880188, "learning_rate": 7.16365754222481e-05, "loss": 0.8598, "step": 493 }, { "epoch": 0.8613775065387969, "grad_norm": 0.7913116216659546, "learning_rate": 7.157833430401864e-05, "loss": 0.8349, "step": 494 }, { "epoch": 0.8631211857018308, "grad_norm": 0.7827887535095215, "learning_rate": 7.152009318578917e-05, "loss": 0.8096, "step": 495 }, { "epoch": 0.8648648648648649, "grad_norm": 0.9174376130104065, "learning_rate": 7.14618520675597e-05, "loss": 0.949, "step": 496 }, { "epoch": 0.8666085440278989, "grad_norm": 0.7872313857078552, "learning_rate": 7.140361094933024e-05, "loss": 0.8597, "step": 497 }, { "epoch": 0.8683522231909329, "grad_norm": 0.7816391587257385, "learning_rate": 7.134536983110076e-05, "loss": 0.8474, "step": 498 }, { "epoch": 0.8700959023539668, "grad_norm": 0.6767029762268066, "learning_rate": 7.128712871287129e-05, "loss": 0.7681, "step": 499 }, { "epoch": 0.8718395815170009, "grad_norm": 0.7776670455932617, "learning_rate": 7.122888759464182e-05, "loss": 0.8269, "step": 500 }, { "epoch": 0.8735832606800349, "grad_norm": 0.9366557002067566, "learning_rate": 7.117064647641234e-05, "loss": 0.8561, "step": 501 }, { "epoch": 0.8753269398430689, "grad_norm": 0.7974362373352051, "learning_rate": 7.111240535818287e-05, "loss": 0.8007, "step": 502 }, { "epoch": 0.8770706190061028, "grad_norm": 0.776149332523346, "learning_rate": 7.105416423995341e-05, "loss": 0.7283, "step": 503 }, { "epoch": 0.8788142981691369, "grad_norm": 0.7463400363922119, "learning_rate": 7.099592312172394e-05, "loss": 0.8085, "step": 504 }, { "epoch": 0.8805579773321709, "grad_norm": 0.7968703508377075, "learning_rate": 7.093768200349447e-05, "loss": 0.8296, "step": 505 }, { "epoch": 0.8823016564952049, "grad_norm": 0.6778225302696228, "learning_rate": 7.0879440885265e-05, "loss": 0.7972, "step": 506 }, { "epoch": 0.8840453356582388, "grad_norm": 0.6663320064544678, "learning_rate": 7.082119976703553e-05, "loss": 0.7677, "step": 507 }, { "epoch": 0.8857890148212729, "grad_norm": 0.6959134340286255, "learning_rate": 7.076295864880606e-05, "loss": 0.7776, "step": 508 }, { "epoch": 0.8875326939843069, "grad_norm": 1.0643547773361206, "learning_rate": 7.070471753057659e-05, "loss": 0.9376, "step": 509 }, { "epoch": 0.8892763731473409, "grad_norm": 0.6571854948997498, "learning_rate": 7.064647641234711e-05, "loss": 0.7928, "step": 510 }, { "epoch": 0.8910200523103748, "grad_norm": 0.8760579824447632, "learning_rate": 7.058823529411765e-05, "loss": 0.9249, "step": 511 }, { "epoch": 0.8927637314734089, "grad_norm": 0.7342020869255066, "learning_rate": 7.052999417588818e-05, "loss": 0.7933, "step": 512 }, { "epoch": 0.8945074106364429, "grad_norm": 0.7267552614212036, "learning_rate": 7.047175305765871e-05, "loss": 0.8903, "step": 513 }, { "epoch": 0.8962510897994769, "grad_norm": 1.0595183372497559, "learning_rate": 7.041351193942925e-05, "loss": 0.9689, "step": 514 }, { "epoch": 0.8979947689625108, "grad_norm": 1.1541802883148193, "learning_rate": 7.035527082119978e-05, "loss": 0.9628, "step": 515 }, { "epoch": 0.8997384481255449, "grad_norm": 0.7945829629898071, "learning_rate": 7.02970297029703e-05, "loss": 0.7762, "step": 516 }, { "epoch": 0.9014821272885789, "grad_norm": 0.8477960824966431, "learning_rate": 7.023878858474083e-05, "loss": 0.8328, "step": 517 }, { "epoch": 0.9032258064516129, "grad_norm": 1.085448980331421, "learning_rate": 7.018054746651136e-05, "loss": 0.7713, "step": 518 }, { "epoch": 0.9049694856146469, "grad_norm": 0.7678982615470886, "learning_rate": 7.012230634828188e-05, "loss": 0.866, "step": 519 }, { "epoch": 0.9067131647776809, "grad_norm": 0.7758105993270874, "learning_rate": 7.006406523005242e-05, "loss": 0.7691, "step": 520 }, { "epoch": 0.9084568439407149, "grad_norm": 0.7943785190582275, "learning_rate": 7.000582411182295e-05, "loss": 0.8144, "step": 521 }, { "epoch": 0.9102005231037489, "grad_norm": 0.7474287152290344, "learning_rate": 6.994758299359349e-05, "loss": 0.7594, "step": 522 }, { "epoch": 0.911944202266783, "grad_norm": 0.7334807515144348, "learning_rate": 6.988934187536402e-05, "loss": 0.7809, "step": 523 }, { "epoch": 0.9136878814298169, "grad_norm": 1.0572025775909424, "learning_rate": 6.983110075713453e-05, "loss": 0.8384, "step": 524 }, { "epoch": 0.9154315605928509, "grad_norm": 1.1457363367080688, "learning_rate": 6.977285963890507e-05, "loss": 0.9221, "step": 525 }, { "epoch": 0.9171752397558849, "grad_norm": 0.6989151239395142, "learning_rate": 6.97146185206756e-05, "loss": 0.8155, "step": 526 }, { "epoch": 0.918918918918919, "grad_norm": 0.8281192183494568, "learning_rate": 6.965637740244613e-05, "loss": 0.7554, "step": 527 }, { "epoch": 0.9206625980819529, "grad_norm": 0.9054682850837708, "learning_rate": 6.959813628421667e-05, "loss": 0.8754, "step": 528 }, { "epoch": 0.9224062772449869, "grad_norm": 0.7522796392440796, "learning_rate": 6.953989516598719e-05, "loss": 0.8628, "step": 529 }, { "epoch": 0.9241499564080209, "grad_norm": 0.7536612153053284, "learning_rate": 6.948165404775772e-05, "loss": 0.6919, "step": 530 }, { "epoch": 0.925893635571055, "grad_norm": 0.7016891837120056, "learning_rate": 6.942341292952825e-05, "loss": 0.8144, "step": 531 }, { "epoch": 0.927637314734089, "grad_norm": 0.7664355635643005, "learning_rate": 6.936517181129877e-05, "loss": 0.8, "step": 532 }, { "epoch": 0.9293809938971229, "grad_norm": 0.709613561630249, "learning_rate": 6.93069306930693e-05, "loss": 0.8108, "step": 533 }, { "epoch": 0.9311246730601569, "grad_norm": 0.7479997277259827, "learning_rate": 6.924868957483984e-05, "loss": 0.8249, "step": 534 }, { "epoch": 0.932868352223191, "grad_norm": 0.8538856506347656, "learning_rate": 6.919044845661037e-05, "loss": 0.7393, "step": 535 }, { "epoch": 0.934612031386225, "grad_norm": 0.9248573184013367, "learning_rate": 6.913220733838091e-05, "loss": 0.9161, "step": 536 }, { "epoch": 0.9363557105492589, "grad_norm": 0.87127286195755, "learning_rate": 6.907396622015144e-05, "loss": 0.8878, "step": 537 }, { "epoch": 0.9380993897122929, "grad_norm": 0.7824704647064209, "learning_rate": 6.901572510192196e-05, "loss": 0.8809, "step": 538 }, { "epoch": 0.939843068875327, "grad_norm": 0.6799480319023132, "learning_rate": 6.895748398369249e-05, "loss": 0.7914, "step": 539 }, { "epoch": 0.941586748038361, "grad_norm": 0.7047470808029175, "learning_rate": 6.889924286546302e-05, "loss": 0.773, "step": 540 }, { "epoch": 0.9433304272013949, "grad_norm": 0.7361706495285034, "learning_rate": 6.884100174723354e-05, "loss": 0.8264, "step": 541 }, { "epoch": 0.9450741063644289, "grad_norm": 0.9195733070373535, "learning_rate": 6.878276062900408e-05, "loss": 0.7944, "step": 542 }, { "epoch": 0.946817785527463, "grad_norm": 0.8126800656318665, "learning_rate": 6.872451951077461e-05, "loss": 0.7991, "step": 543 }, { "epoch": 0.948561464690497, "grad_norm": 0.7375898957252502, "learning_rate": 6.866627839254514e-05, "loss": 0.7812, "step": 544 }, { "epoch": 0.9503051438535309, "grad_norm": 0.8873994946479797, "learning_rate": 6.860803727431568e-05, "loss": 0.882, "step": 545 }, { "epoch": 0.9520488230165649, "grad_norm": 0.8705134987831116, "learning_rate": 6.85497961560862e-05, "loss": 0.7933, "step": 546 }, { "epoch": 0.953792502179599, "grad_norm": 0.8558249473571777, "learning_rate": 6.849155503785673e-05, "loss": 0.8068, "step": 547 }, { "epoch": 0.955536181342633, "grad_norm": 0.8098289370536804, "learning_rate": 6.843331391962726e-05, "loss": 0.8131, "step": 548 }, { "epoch": 0.9572798605056669, "grad_norm": 1.6549385786056519, "learning_rate": 6.837507280139779e-05, "loss": 0.9536, "step": 549 }, { "epoch": 0.9590235396687009, "grad_norm": 0.8537018299102783, "learning_rate": 6.831683168316833e-05, "loss": 0.8949, "step": 550 }, { "epoch": 0.960767218831735, "grad_norm": 0.7175675630569458, "learning_rate": 6.825859056493885e-05, "loss": 0.7949, "step": 551 }, { "epoch": 0.962510897994769, "grad_norm": 0.7517974376678467, "learning_rate": 6.820034944670938e-05, "loss": 0.8273, "step": 552 }, { "epoch": 0.9642545771578029, "grad_norm": 0.7322865128517151, "learning_rate": 6.814210832847992e-05, "loss": 0.7625, "step": 553 }, { "epoch": 0.9659982563208369, "grad_norm": 0.6688904166221619, "learning_rate": 6.808386721025045e-05, "loss": 0.7707, "step": 554 }, { "epoch": 0.967741935483871, "grad_norm": 0.7775446176528931, "learning_rate": 6.802562609202096e-05, "loss": 0.8678, "step": 555 }, { "epoch": 0.969485614646905, "grad_norm": 0.7365615367889404, "learning_rate": 6.79673849737915e-05, "loss": 0.8177, "step": 556 }, { "epoch": 0.9712292938099389, "grad_norm": 0.6888483762741089, "learning_rate": 6.790914385556203e-05, "loss": 0.7864, "step": 557 }, { "epoch": 0.972972972972973, "grad_norm": 0.6689252853393555, "learning_rate": 6.785090273733255e-05, "loss": 0.7791, "step": 558 }, { "epoch": 0.974716652136007, "grad_norm": 0.8840147852897644, "learning_rate": 6.77926616191031e-05, "loss": 0.8382, "step": 559 }, { "epoch": 0.976460331299041, "grad_norm": 0.9517379999160767, "learning_rate": 6.773442050087362e-05, "loss": 0.9589, "step": 560 }, { "epoch": 0.978204010462075, "grad_norm": 0.9505780935287476, "learning_rate": 6.767617938264415e-05, "loss": 0.8811, "step": 561 }, { "epoch": 0.979947689625109, "grad_norm": 0.8270111083984375, "learning_rate": 6.761793826441468e-05, "loss": 0.8437, "step": 562 }, { "epoch": 0.981691368788143, "grad_norm": 0.752602219581604, "learning_rate": 6.75596971461852e-05, "loss": 0.7952, "step": 563 }, { "epoch": 0.983435047951177, "grad_norm": 1.0673571825027466, "learning_rate": 6.750145602795574e-05, "loss": 0.8661, "step": 564 }, { "epoch": 0.985178727114211, "grad_norm": 0.6674084663391113, "learning_rate": 6.744321490972627e-05, "loss": 0.7947, "step": 565 }, { "epoch": 0.986922406277245, "grad_norm": 0.9393231868743896, "learning_rate": 6.73849737914968e-05, "loss": 0.8725, "step": 566 }, { "epoch": 0.988666085440279, "grad_norm": 0.8054789900779724, "learning_rate": 6.732673267326734e-05, "loss": 0.8156, "step": 567 }, { "epoch": 0.990409764603313, "grad_norm": 0.6786013245582581, "learning_rate": 6.726849155503786e-05, "loss": 0.8052, "step": 568 }, { "epoch": 0.992153443766347, "grad_norm": 0.804745614528656, "learning_rate": 6.721025043680839e-05, "loss": 0.9271, "step": 569 }, { "epoch": 0.993897122929381, "grad_norm": 0.7803003787994385, "learning_rate": 6.715200931857892e-05, "loss": 0.7904, "step": 570 }, { "epoch": 0.995640802092415, "grad_norm": 0.9034241437911987, "learning_rate": 6.709376820034945e-05, "loss": 0.8346, "step": 571 }, { "epoch": 0.997384481255449, "grad_norm": 0.7823648452758789, "learning_rate": 6.703552708211997e-05, "loss": 0.7946, "step": 572 }, { "epoch": 0.999128160418483, "grad_norm": 0.8454820513725281, "learning_rate": 6.697728596389051e-05, "loss": 0.7896, "step": 573 }, { "epoch": 1.0, "grad_norm": 1.3399591445922852, "learning_rate": 6.691904484566104e-05, "loss": 0.8935, "step": 574 }, { "epoch": 1.001743679163034, "grad_norm": 0.8516078591346741, "learning_rate": 6.686080372743157e-05, "loss": 0.6733, "step": 575 }, { "epoch": 1.003487358326068, "grad_norm": 0.8038057684898376, "learning_rate": 6.680256260920211e-05, "loss": 0.6301, "step": 576 }, { "epoch": 1.005231037489102, "grad_norm": 0.8145012855529785, "learning_rate": 6.674432149097263e-05, "loss": 0.5567, "step": 577 }, { "epoch": 1.0069747166521361, "grad_norm": 0.9676138162612915, "learning_rate": 6.668608037274316e-05, "loss": 0.6586, "step": 578 }, { "epoch": 1.00871839581517, "grad_norm": 0.8368747234344482, "learning_rate": 6.662783925451369e-05, "loss": 0.6454, "step": 579 }, { "epoch": 1.010462074978204, "grad_norm": 0.748993992805481, "learning_rate": 6.656959813628421e-05, "loss": 0.6095, "step": 580 }, { "epoch": 1.012205754141238, "grad_norm": 1.0748870372772217, "learning_rate": 6.651135701805476e-05, "loss": 0.696, "step": 581 }, { "epoch": 1.013949433304272, "grad_norm": 0.8404095768928528, "learning_rate": 6.645311589982528e-05, "loss": 0.5588, "step": 582 }, { "epoch": 1.015693112467306, "grad_norm": 1.073421835899353, "learning_rate": 6.639487478159581e-05, "loss": 0.6848, "step": 583 }, { "epoch": 1.01743679163034, "grad_norm": 1.3154810667037964, "learning_rate": 6.633663366336635e-05, "loss": 0.7313, "step": 584 }, { "epoch": 1.019180470793374, "grad_norm": 0.8173841238021851, "learning_rate": 6.627839254513686e-05, "loss": 0.5957, "step": 585 }, { "epoch": 1.0209241499564081, "grad_norm": 1.3077826499938965, "learning_rate": 6.622015142690739e-05, "loss": 0.6829, "step": 586 }, { "epoch": 1.022667829119442, "grad_norm": 1.0066320896148682, "learning_rate": 6.616191030867793e-05, "loss": 0.6907, "step": 587 }, { "epoch": 1.024411508282476, "grad_norm": 0.9567937850952148, "learning_rate": 6.610366919044846e-05, "loss": 0.6148, "step": 588 }, { "epoch": 1.02615518744551, "grad_norm": 1.0344828367233276, "learning_rate": 6.604542807221898e-05, "loss": 0.6189, "step": 589 }, { "epoch": 1.027898866608544, "grad_norm": 0.7941462397575378, "learning_rate": 6.598718695398952e-05, "loss": 0.5657, "step": 590 }, { "epoch": 1.029642545771578, "grad_norm": 1.0554827451705933, "learning_rate": 6.592894583576005e-05, "loss": 0.6538, "step": 591 }, { "epoch": 1.031386224934612, "grad_norm": 0.9092023968696594, "learning_rate": 6.587070471753058e-05, "loss": 0.6138, "step": 592 }, { "epoch": 1.033129904097646, "grad_norm": 0.8296151757240295, "learning_rate": 6.58124635993011e-05, "loss": 0.5811, "step": 593 }, { "epoch": 1.0348735832606801, "grad_norm": 0.8269428014755249, "learning_rate": 6.575422248107163e-05, "loss": 0.6375, "step": 594 }, { "epoch": 1.036617262423714, "grad_norm": 0.7058696746826172, "learning_rate": 6.569598136284217e-05, "loss": 0.5328, "step": 595 }, { "epoch": 1.038360941586748, "grad_norm": 0.7724451422691345, "learning_rate": 6.56377402446127e-05, "loss": 0.5724, "step": 596 }, { "epoch": 1.040104620749782, "grad_norm": 0.946164071559906, "learning_rate": 6.557949912638323e-05, "loss": 0.5979, "step": 597 }, { "epoch": 1.041848299912816, "grad_norm": 0.8750537037849426, "learning_rate": 6.552125800815377e-05, "loss": 0.643, "step": 598 }, { "epoch": 1.04359197907585, "grad_norm": 0.9916619658470154, "learning_rate": 6.54630168899243e-05, "loss": 0.6582, "step": 599 }, { "epoch": 1.045335658238884, "grad_norm": 0.7821680903434753, "learning_rate": 6.540477577169482e-05, "loss": 0.5695, "step": 600 }, { "epoch": 1.047079337401918, "grad_norm": 0.81645667552948, "learning_rate": 6.534653465346535e-05, "loss": 0.586, "step": 601 }, { "epoch": 1.0488230165649521, "grad_norm": 1.1194818019866943, "learning_rate": 6.528829353523587e-05, "loss": 0.5926, "step": 602 }, { "epoch": 1.050566695727986, "grad_norm": 0.7025761604309082, "learning_rate": 6.52300524170064e-05, "loss": 0.5593, "step": 603 }, { "epoch": 1.05231037489102, "grad_norm": 1.2246297597885132, "learning_rate": 6.517181129877694e-05, "loss": 0.697, "step": 604 }, { "epoch": 1.054054054054054, "grad_norm": 1.0729471445083618, "learning_rate": 6.511357018054747e-05, "loss": 0.6512, "step": 605 }, { "epoch": 1.055797733217088, "grad_norm": 0.8863468766212463, "learning_rate": 6.505532906231801e-05, "loss": 0.6285, "step": 606 }, { "epoch": 1.0575414123801221, "grad_norm": 0.7570905089378357, "learning_rate": 6.499708794408854e-05, "loss": 0.4967, "step": 607 }, { "epoch": 1.059285091543156, "grad_norm": 0.9872047305107117, "learning_rate": 6.493884682585906e-05, "loss": 0.6179, "step": 608 }, { "epoch": 1.06102877070619, "grad_norm": 1.042121171951294, "learning_rate": 6.488060570762959e-05, "loss": 0.6853, "step": 609 }, { "epoch": 1.0627724498692241, "grad_norm": 0.9903281927108765, "learning_rate": 6.482236458940012e-05, "loss": 0.6303, "step": 610 }, { "epoch": 1.064516129032258, "grad_norm": 1.069576382637024, "learning_rate": 6.476412347117064e-05, "loss": 0.668, "step": 611 }, { "epoch": 1.066259808195292, "grad_norm": 0.9160135984420776, "learning_rate": 6.470588235294118e-05, "loss": 0.6379, "step": 612 }, { "epoch": 1.0680034873583262, "grad_norm": 0.886971116065979, "learning_rate": 6.464764123471171e-05, "loss": 0.6296, "step": 613 }, { "epoch": 1.06974716652136, "grad_norm": 0.8684503436088562, "learning_rate": 6.458940011648224e-05, "loss": 0.6195, "step": 614 }, { "epoch": 1.0714908456843941, "grad_norm": 0.9829879999160767, "learning_rate": 6.453115899825278e-05, "loss": 0.4933, "step": 615 }, { "epoch": 1.073234524847428, "grad_norm": 1.1317808628082275, "learning_rate": 6.447291788002329e-05, "loss": 0.6889, "step": 616 }, { "epoch": 1.074978204010462, "grad_norm": 0.8370760679244995, "learning_rate": 6.441467676179382e-05, "loss": 0.681, "step": 617 }, { "epoch": 1.0767218831734962, "grad_norm": 0.7394255995750427, "learning_rate": 6.435643564356436e-05, "loss": 0.5586, "step": 618 }, { "epoch": 1.07846556233653, "grad_norm": 0.8756667971611023, "learning_rate": 6.429819452533489e-05, "loss": 0.5607, "step": 619 }, { "epoch": 1.080209241499564, "grad_norm": 0.7498895525932312, "learning_rate": 6.423995340710543e-05, "loss": 0.5497, "step": 620 }, { "epoch": 1.0819529206625982, "grad_norm": 0.943362295627594, "learning_rate": 6.418171228887595e-05, "loss": 0.6804, "step": 621 }, { "epoch": 1.083696599825632, "grad_norm": 1.0392085313796997, "learning_rate": 6.412347117064648e-05, "loss": 0.5999, "step": 622 }, { "epoch": 1.0854402789886661, "grad_norm": 1.224944829940796, "learning_rate": 6.406523005241701e-05, "loss": 0.7058, "step": 623 }, { "epoch": 1.0871839581517, "grad_norm": 0.9203630089759827, "learning_rate": 6.400698893418753e-05, "loss": 0.6074, "step": 624 }, { "epoch": 1.088927637314734, "grad_norm": 1.0283782482147217, "learning_rate": 6.394874781595806e-05, "loss": 0.6701, "step": 625 }, { "epoch": 1.0906713164777682, "grad_norm": 1.0126944780349731, "learning_rate": 6.38905066977286e-05, "loss": 0.6564, "step": 626 }, { "epoch": 1.092414995640802, "grad_norm": 0.9231863021850586, "learning_rate": 6.383226557949913e-05, "loss": 0.6067, "step": 627 }, { "epoch": 1.094158674803836, "grad_norm": 0.9525390267372131, "learning_rate": 6.377402446126966e-05, "loss": 0.6285, "step": 628 }, { "epoch": 1.0959023539668702, "grad_norm": 0.719582200050354, "learning_rate": 6.37157833430402e-05, "loss": 0.4976, "step": 629 }, { "epoch": 1.097646033129904, "grad_norm": 1.0390384197235107, "learning_rate": 6.365754222481072e-05, "loss": 0.6784, "step": 630 }, { "epoch": 1.0993897122929381, "grad_norm": 0.875333309173584, "learning_rate": 6.359930110658125e-05, "loss": 0.6324, "step": 631 }, { "epoch": 1.101133391455972, "grad_norm": 0.7112342119216919, "learning_rate": 6.354105998835178e-05, "loss": 0.534, "step": 632 }, { "epoch": 1.102877070619006, "grad_norm": 1.1255197525024414, "learning_rate": 6.34828188701223e-05, "loss": 0.6891, "step": 633 }, { "epoch": 1.1046207497820402, "grad_norm": 0.9505216479301453, "learning_rate": 6.342457775189284e-05, "loss": 0.6365, "step": 634 }, { "epoch": 1.106364428945074, "grad_norm": 1.0356428623199463, "learning_rate": 6.336633663366337e-05, "loss": 0.6982, "step": 635 }, { "epoch": 1.1081081081081081, "grad_norm": 1.124653935432434, "learning_rate": 6.33080955154339e-05, "loss": 0.6641, "step": 636 }, { "epoch": 1.1098517872711422, "grad_norm": 0.8968854546546936, "learning_rate": 6.324985439720444e-05, "loss": 0.6296, "step": 637 }, { "epoch": 1.111595466434176, "grad_norm": 0.7717108130455017, "learning_rate": 6.319161327897497e-05, "loss": 0.4811, "step": 638 }, { "epoch": 1.1133391455972101, "grad_norm": 0.876542866230011, "learning_rate": 6.313337216074548e-05, "loss": 0.6072, "step": 639 }, { "epoch": 1.1150828247602442, "grad_norm": 1.1441415548324585, "learning_rate": 6.307513104251602e-05, "loss": 0.642, "step": 640 }, { "epoch": 1.116826503923278, "grad_norm": 0.8067407011985779, "learning_rate": 6.301688992428655e-05, "loss": 0.6343, "step": 641 }, { "epoch": 1.1185701830863122, "grad_norm": 0.7515537738800049, "learning_rate": 6.295864880605707e-05, "loss": 0.5286, "step": 642 }, { "epoch": 1.120313862249346, "grad_norm": 0.8026893734931946, "learning_rate": 6.290040768782761e-05, "loss": 0.4844, "step": 643 }, { "epoch": 1.1220575414123801, "grad_norm": 0.9571293592453003, "learning_rate": 6.284216656959814e-05, "loss": 0.6636, "step": 644 }, { "epoch": 1.1238012205754142, "grad_norm": 0.8107324838638306, "learning_rate": 6.278392545136868e-05, "loss": 0.5804, "step": 645 }, { "epoch": 1.125544899738448, "grad_norm": 0.9457992315292358, "learning_rate": 6.27256843331392e-05, "loss": 0.621, "step": 646 }, { "epoch": 1.1272885789014822, "grad_norm": 1.1062275171279907, "learning_rate": 6.266744321490972e-05, "loss": 0.5247, "step": 647 }, { "epoch": 1.129032258064516, "grad_norm": 1.1840991973876953, "learning_rate": 6.260920209668026e-05, "loss": 0.6959, "step": 648 }, { "epoch": 1.13077593722755, "grad_norm": 1.053908109664917, "learning_rate": 6.255096097845079e-05, "loss": 0.6479, "step": 649 }, { "epoch": 1.1325196163905842, "grad_norm": 0.7999213933944702, "learning_rate": 6.249271986022132e-05, "loss": 0.6082, "step": 650 }, { "epoch": 1.134263295553618, "grad_norm": 0.9403919577598572, "learning_rate": 6.243447874199186e-05, "loss": 0.6295, "step": 651 }, { "epoch": 1.1360069747166521, "grad_norm": 0.9612235426902771, "learning_rate": 6.237623762376238e-05, "loss": 0.6372, "step": 652 }, { "epoch": 1.1377506538796862, "grad_norm": 0.8416748046875, "learning_rate": 6.231799650553291e-05, "loss": 0.5229, "step": 653 }, { "epoch": 1.13949433304272, "grad_norm": 0.8808147311210632, "learning_rate": 6.225975538730344e-05, "loss": 0.617, "step": 654 }, { "epoch": 1.1412380122057542, "grad_norm": 0.8570967316627502, "learning_rate": 6.220151426907396e-05, "loss": 0.6135, "step": 655 }, { "epoch": 1.1429816913687882, "grad_norm": 0.9354975819587708, "learning_rate": 6.214327315084449e-05, "loss": 0.5672, "step": 656 }, { "epoch": 1.144725370531822, "grad_norm": 0.9145675897598267, "learning_rate": 6.208503203261503e-05, "loss": 0.539, "step": 657 }, { "epoch": 1.1464690496948562, "grad_norm": 1.0136606693267822, "learning_rate": 6.202679091438556e-05, "loss": 0.6274, "step": 658 }, { "epoch": 1.14821272885789, "grad_norm": 0.8981542587280273, "learning_rate": 6.19685497961561e-05, "loss": 0.589, "step": 659 }, { "epoch": 1.1499564080209241, "grad_norm": 1.0708802938461304, "learning_rate": 6.191030867792663e-05, "loss": 0.5964, "step": 660 }, { "epoch": 1.1517000871839582, "grad_norm": 1.1797173023223877, "learning_rate": 6.185206755969715e-05, "loss": 0.6711, "step": 661 }, { "epoch": 1.153443766346992, "grad_norm": 1.0411361455917358, "learning_rate": 6.179382644146768e-05, "loss": 0.6584, "step": 662 }, { "epoch": 1.1551874455100262, "grad_norm": 0.8597391247749329, "learning_rate": 6.17355853232382e-05, "loss": 0.5752, "step": 663 }, { "epoch": 1.1569311246730603, "grad_norm": 0.9313083291053772, "learning_rate": 6.167734420500873e-05, "loss": 0.5795, "step": 664 }, { "epoch": 1.1586748038360941, "grad_norm": 0.9896420836448669, "learning_rate": 6.161910308677927e-05, "loss": 0.6427, "step": 665 }, { "epoch": 1.1604184829991282, "grad_norm": 0.7842606902122498, "learning_rate": 6.15608619685498e-05, "loss": 0.6142, "step": 666 }, { "epoch": 1.1621621621621623, "grad_norm": 0.7937389612197876, "learning_rate": 6.150262085032033e-05, "loss": 0.528, "step": 667 }, { "epoch": 1.1639058413251961, "grad_norm": 0.8045235872268677, "learning_rate": 6.144437973209087e-05, "loss": 0.5751, "step": 668 }, { "epoch": 1.1656495204882302, "grad_norm": 0.9443396329879761, "learning_rate": 6.13861386138614e-05, "loss": 0.6005, "step": 669 }, { "epoch": 1.167393199651264, "grad_norm": 0.8722188472747803, "learning_rate": 6.132789749563191e-05, "loss": 0.6322, "step": 670 }, { "epoch": 1.1691368788142982, "grad_norm": 0.7327280640602112, "learning_rate": 6.126965637740245e-05, "loss": 0.5525, "step": 671 }, { "epoch": 1.1708805579773323, "grad_norm": 0.9708648920059204, "learning_rate": 6.121141525917298e-05, "loss": 0.6024, "step": 672 }, { "epoch": 1.1726242371403661, "grad_norm": 0.9882156252861023, "learning_rate": 6.115317414094352e-05, "loss": 0.6695, "step": 673 }, { "epoch": 1.1743679163034002, "grad_norm": 1.0703502893447876, "learning_rate": 6.109493302271404e-05, "loss": 0.6736, "step": 674 }, { "epoch": 1.176111595466434, "grad_norm": 0.8511261343955994, "learning_rate": 6.103669190448457e-05, "loss": 0.5841, "step": 675 }, { "epoch": 1.1778552746294682, "grad_norm": 1.1165263652801514, "learning_rate": 6.09784507862551e-05, "loss": 0.5817, "step": 676 }, { "epoch": 1.1795989537925022, "grad_norm": 0.8287544846534729, "learning_rate": 6.092020966802563e-05, "loss": 0.5818, "step": 677 }, { "epoch": 1.181342632955536, "grad_norm": 0.8827126026153564, "learning_rate": 6.086196854979616e-05, "loss": 0.6239, "step": 678 }, { "epoch": 1.1830863121185702, "grad_norm": 0.8665584921836853, "learning_rate": 6.080372743156669e-05, "loss": 0.5235, "step": 679 }, { "epoch": 1.1848299912816043, "grad_norm": 0.8452827334403992, "learning_rate": 6.074548631333722e-05, "loss": 0.6074, "step": 680 }, { "epoch": 1.1865736704446381, "grad_norm": 1.2033249139785767, "learning_rate": 6.0687245195107745e-05, "loss": 0.6741, "step": 681 }, { "epoch": 1.1883173496076722, "grad_norm": 0.8630607724189758, "learning_rate": 6.0629004076878285e-05, "loss": 0.6475, "step": 682 }, { "epoch": 1.1900610287707063, "grad_norm": 0.8493909239768982, "learning_rate": 6.0570762958648805e-05, "loss": 0.595, "step": 683 }, { "epoch": 1.1918047079337402, "grad_norm": 1.1724084615707397, "learning_rate": 6.051252184041933e-05, "loss": 0.7033, "step": 684 }, { "epoch": 1.1935483870967742, "grad_norm": 0.8539560437202454, "learning_rate": 6.045428072218987e-05, "loss": 0.5477, "step": 685 }, { "epoch": 1.195292066259808, "grad_norm": 0.9539121985435486, "learning_rate": 6.03960396039604e-05, "loss": 0.6217, "step": 686 }, { "epoch": 1.1970357454228422, "grad_norm": 0.9616498351097107, "learning_rate": 6.033779848573093e-05, "loss": 0.6496, "step": 687 }, { "epoch": 1.1987794245858763, "grad_norm": 0.9076695442199707, "learning_rate": 6.027955736750146e-05, "loss": 0.5861, "step": 688 }, { "epoch": 1.2005231037489101, "grad_norm": 0.9249758720397949, "learning_rate": 6.022131624927199e-05, "loss": 0.648, "step": 689 }, { "epoch": 1.2022667829119442, "grad_norm": 0.8361638784408569, "learning_rate": 6.016307513104252e-05, "loss": 0.5558, "step": 690 }, { "epoch": 1.204010462074978, "grad_norm": 0.7910105586051941, "learning_rate": 6.010483401281305e-05, "loss": 0.5654, "step": 691 }, { "epoch": 1.2057541412380122, "grad_norm": 1.1203887462615967, "learning_rate": 6.0046592894583575e-05, "loss": 0.6857, "step": 692 }, { "epoch": 1.2074978204010463, "grad_norm": 1.055227279663086, "learning_rate": 5.9988351776354115e-05, "loss": 0.6155, "step": 693 }, { "epoch": 1.2092414995640801, "grad_norm": 0.8544262647628784, "learning_rate": 5.9930110658124635e-05, "loss": 0.5377, "step": 694 }, { "epoch": 1.2109851787271142, "grad_norm": 1.232897400856018, "learning_rate": 5.987186953989516e-05, "loss": 0.643, "step": 695 }, { "epoch": 1.2127288578901483, "grad_norm": 0.927211582660675, "learning_rate": 5.98136284216657e-05, "loss": 0.507, "step": 696 }, { "epoch": 1.2144725370531821, "grad_norm": 0.8092779517173767, "learning_rate": 5.975538730343623e-05, "loss": 0.5873, "step": 697 }, { "epoch": 1.2162162162162162, "grad_norm": 0.9790780544281006, "learning_rate": 5.9697146185206756e-05, "loss": 0.6151, "step": 698 }, { "epoch": 1.2179598953792503, "grad_norm": 0.834092915058136, "learning_rate": 5.963890506697729e-05, "loss": 0.5577, "step": 699 }, { "epoch": 1.2197035745422842, "grad_norm": 0.8697766065597534, "learning_rate": 5.958066394874782e-05, "loss": 0.6324, "step": 700 }, { "epoch": 1.2214472537053183, "grad_norm": 0.8395124077796936, "learning_rate": 5.952242283051835e-05, "loss": 0.6168, "step": 701 }, { "epoch": 1.2231909328683521, "grad_norm": 1.093450665473938, "learning_rate": 5.946418171228888e-05, "loss": 0.7167, "step": 702 }, { "epoch": 1.2249346120313862, "grad_norm": 0.9852606058120728, "learning_rate": 5.9405940594059404e-05, "loss": 0.7215, "step": 703 }, { "epoch": 1.2266782911944203, "grad_norm": 0.7893871068954468, "learning_rate": 5.9347699475829945e-05, "loss": 0.5279, "step": 704 }, { "epoch": 1.2284219703574542, "grad_norm": 0.9453630447387695, "learning_rate": 5.928945835760047e-05, "loss": 0.635, "step": 705 }, { "epoch": 1.2301656495204882, "grad_norm": 1.1252881288528442, "learning_rate": 5.923121723937099e-05, "loss": 0.6468, "step": 706 }, { "epoch": 1.2319093286835223, "grad_norm": 0.7241825461387634, "learning_rate": 5.917297612114153e-05, "loss": 0.5374, "step": 707 }, { "epoch": 1.2336530078465562, "grad_norm": 0.7870163321495056, "learning_rate": 5.911473500291206e-05, "loss": 0.5495, "step": 708 }, { "epoch": 1.2353966870095903, "grad_norm": 0.9549890160560608, "learning_rate": 5.9056493884682586e-05, "loss": 0.5528, "step": 709 }, { "epoch": 1.2371403661726244, "grad_norm": 0.843959629535675, "learning_rate": 5.899825276645312e-05, "loss": 0.549, "step": 710 }, { "epoch": 1.2388840453356582, "grad_norm": 0.7966902256011963, "learning_rate": 5.894001164822365e-05, "loss": 0.5345, "step": 711 }, { "epoch": 1.2406277244986923, "grad_norm": 0.9975771307945251, "learning_rate": 5.8881770529994174e-05, "loss": 0.5797, "step": 712 }, { "epoch": 1.2423714036617262, "grad_norm": 0.8149213194847107, "learning_rate": 5.882352941176471e-05, "loss": 0.5782, "step": 713 }, { "epoch": 1.2441150828247602, "grad_norm": 1.1083334684371948, "learning_rate": 5.8765288293535234e-05, "loss": 0.5387, "step": 714 }, { "epoch": 1.2458587619877943, "grad_norm": 0.987398087978363, "learning_rate": 5.8707047175305775e-05, "loss": 0.6407, "step": 715 }, { "epoch": 1.2476024411508282, "grad_norm": 1.1867581605911255, "learning_rate": 5.86488060570763e-05, "loss": 0.592, "step": 716 }, { "epoch": 1.2493461203138623, "grad_norm": 0.9550538063049316, "learning_rate": 5.859056493884683e-05, "loss": 0.5868, "step": 717 }, { "epoch": 1.2510897994768961, "grad_norm": 0.830379068851471, "learning_rate": 5.853232382061736e-05, "loss": 0.6109, "step": 718 }, { "epoch": 1.2528334786399302, "grad_norm": 1.1827552318572998, "learning_rate": 5.847408270238789e-05, "loss": 0.6212, "step": 719 }, { "epoch": 1.2545771578029643, "grad_norm": 0.7931007146835327, "learning_rate": 5.8415841584158416e-05, "loss": 0.6004, "step": 720 }, { "epoch": 1.2563208369659984, "grad_norm": 1.002324104309082, "learning_rate": 5.835760046592895e-05, "loss": 0.6036, "step": 721 }, { "epoch": 1.2580645161290323, "grad_norm": 1.0522494316101074, "learning_rate": 5.829935934769948e-05, "loss": 0.626, "step": 722 }, { "epoch": 1.2598081952920663, "grad_norm": 0.9524539113044739, "learning_rate": 5.8241118229470004e-05, "loss": 0.6348, "step": 723 }, { "epoch": 1.2615518744551002, "grad_norm": 0.8766840696334839, "learning_rate": 5.8182877111240544e-05, "loss": 0.6014, "step": 724 }, { "epoch": 1.2632955536181343, "grad_norm": 0.9067710041999817, "learning_rate": 5.8124635993011064e-05, "loss": 0.5899, "step": 725 }, { "epoch": 1.2650392327811684, "grad_norm": 1.055791974067688, "learning_rate": 5.806639487478159e-05, "loss": 0.6079, "step": 726 }, { "epoch": 1.2667829119442022, "grad_norm": 0.9391196966171265, "learning_rate": 5.800815375655213e-05, "loss": 0.5721, "step": 727 }, { "epoch": 1.2685265911072363, "grad_norm": 0.9253929853439331, "learning_rate": 5.794991263832266e-05, "loss": 0.5717, "step": 728 }, { "epoch": 1.2702702702702702, "grad_norm": 0.906162440776825, "learning_rate": 5.789167152009319e-05, "loss": 0.6162, "step": 729 }, { "epoch": 1.2720139494333043, "grad_norm": 0.8679141998291016, "learning_rate": 5.783343040186372e-05, "loss": 0.528, "step": 730 }, { "epoch": 1.2737576285963383, "grad_norm": 0.9084288477897644, "learning_rate": 5.7775189283634246e-05, "loss": 0.6201, "step": 731 }, { "epoch": 1.2755013077593722, "grad_norm": 0.905855119228363, "learning_rate": 5.771694816540478e-05, "loss": 0.6107, "step": 732 }, { "epoch": 1.2772449869224063, "grad_norm": 0.8363732099533081, "learning_rate": 5.765870704717531e-05, "loss": 0.5196, "step": 733 }, { "epoch": 1.2789886660854402, "grad_norm": 1.0252721309661865, "learning_rate": 5.7600465928945834e-05, "loss": 0.5398, "step": 734 }, { "epoch": 1.2807323452484742, "grad_norm": 1.2300103902816772, "learning_rate": 5.7542224810716374e-05, "loss": 0.6927, "step": 735 }, { "epoch": 1.2824760244115083, "grad_norm": 0.9767608642578125, "learning_rate": 5.74839836924869e-05, "loss": 0.5141, "step": 736 }, { "epoch": 1.2842197035745424, "grad_norm": 0.8986027836799622, "learning_rate": 5.742574257425742e-05, "loss": 0.5879, "step": 737 }, { "epoch": 1.2859633827375763, "grad_norm": 1.0648634433746338, "learning_rate": 5.736750145602796e-05, "loss": 0.5794, "step": 738 }, { "epoch": 1.2877070619006104, "grad_norm": 1.2186201810836792, "learning_rate": 5.730926033779849e-05, "loss": 0.6958, "step": 739 }, { "epoch": 1.2894507410636442, "grad_norm": 0.7873010635375977, "learning_rate": 5.7251019219569015e-05, "loss": 0.4907, "step": 740 }, { "epoch": 1.2911944202266783, "grad_norm": 0.9607309103012085, "learning_rate": 5.719277810133955e-05, "loss": 0.6246, "step": 741 }, { "epoch": 1.2929380993897124, "grad_norm": 0.9935445189476013, "learning_rate": 5.7134536983110076e-05, "loss": 0.6662, "step": 742 }, { "epoch": 1.2946817785527462, "grad_norm": 0.8454535007476807, "learning_rate": 5.7076295864880617e-05, "loss": 0.555, "step": 743 }, { "epoch": 1.2964254577157803, "grad_norm": 0.8913951516151428, "learning_rate": 5.701805474665114e-05, "loss": 0.589, "step": 744 }, { "epoch": 1.2981691368788142, "grad_norm": 0.8536214232444763, "learning_rate": 5.6959813628421664e-05, "loss": 0.5486, "step": 745 }, { "epoch": 1.2999128160418483, "grad_norm": 1.1809695959091187, "learning_rate": 5.6901572510192204e-05, "loss": 0.6455, "step": 746 }, { "epoch": 1.3016564952048824, "grad_norm": 1.1702719926834106, "learning_rate": 5.684333139196273e-05, "loss": 0.6479, "step": 747 }, { "epoch": 1.3034001743679164, "grad_norm": 0.8880762457847595, "learning_rate": 5.678509027373326e-05, "loss": 0.5776, "step": 748 }, { "epoch": 1.3051438535309503, "grad_norm": 1.0867820978164673, "learning_rate": 5.672684915550379e-05, "loss": 0.6403, "step": 749 }, { "epoch": 1.3068875326939844, "grad_norm": 0.7879469990730286, "learning_rate": 5.666860803727432e-05, "loss": 0.6256, "step": 750 }, { "epoch": 1.3086312118570183, "grad_norm": 0.8784351944923401, "learning_rate": 5.6610366919044845e-05, "loss": 0.5264, "step": 751 }, { "epoch": 1.3103748910200523, "grad_norm": 1.1156294345855713, "learning_rate": 5.655212580081538e-05, "loss": 0.6702, "step": 752 }, { "epoch": 1.3121185701830864, "grad_norm": 0.9888447523117065, "learning_rate": 5.6493884682585906e-05, "loss": 0.659, "step": 753 }, { "epoch": 1.3138622493461203, "grad_norm": 1.012602686882019, "learning_rate": 5.643564356435643e-05, "loss": 0.5866, "step": 754 }, { "epoch": 1.3156059285091544, "grad_norm": 0.8012875318527222, "learning_rate": 5.637740244612697e-05, "loss": 0.5433, "step": 755 }, { "epoch": 1.3173496076721882, "grad_norm": 0.807904064655304, "learning_rate": 5.6319161327897494e-05, "loss": 0.5624, "step": 756 }, { "epoch": 1.3190932868352223, "grad_norm": 0.9894817471504211, "learning_rate": 5.6260920209668034e-05, "loss": 0.5882, "step": 757 }, { "epoch": 1.3208369659982564, "grad_norm": 0.904775857925415, "learning_rate": 5.620267909143856e-05, "loss": 0.5512, "step": 758 }, { "epoch": 1.3225806451612903, "grad_norm": 1.1322146654129028, "learning_rate": 5.614443797320909e-05, "loss": 0.6781, "step": 759 }, { "epoch": 1.3243243243243243, "grad_norm": 0.7874497771263123, "learning_rate": 5.608619685497962e-05, "loss": 0.5065, "step": 760 }, { "epoch": 1.3260680034873582, "grad_norm": 0.8325422406196594, "learning_rate": 5.602795573675015e-05, "loss": 0.5472, "step": 761 }, { "epoch": 1.3278116826503923, "grad_norm": 0.7802289128303528, "learning_rate": 5.5969714618520675e-05, "loss": 0.5303, "step": 762 }, { "epoch": 1.3295553618134264, "grad_norm": 1.0325878858566284, "learning_rate": 5.591147350029121e-05, "loss": 0.6034, "step": 763 }, { "epoch": 1.3312990409764605, "grad_norm": 0.914903998374939, "learning_rate": 5.5853232382061736e-05, "loss": 0.5545, "step": 764 }, { "epoch": 1.3330427201394943, "grad_norm": 0.9257997870445251, "learning_rate": 5.579499126383226e-05, "loss": 0.6029, "step": 765 }, { "epoch": 1.3347863993025284, "grad_norm": 0.8420501351356506, "learning_rate": 5.57367501456028e-05, "loss": 0.588, "step": 766 }, { "epoch": 1.3365300784655623, "grad_norm": 0.9642730355262756, "learning_rate": 5.5678509027373323e-05, "loss": 0.5162, "step": 767 }, { "epoch": 1.3382737576285963, "grad_norm": 0.8962741494178772, "learning_rate": 5.562026790914385e-05, "loss": 0.6188, "step": 768 }, { "epoch": 1.3400174367916304, "grad_norm": 1.0006240606307983, "learning_rate": 5.556202679091439e-05, "loss": 0.6105, "step": 769 }, { "epoch": 1.3417611159546643, "grad_norm": 0.9685559272766113, "learning_rate": 5.550378567268492e-05, "loss": 0.6695, "step": 770 }, { "epoch": 1.3435047951176984, "grad_norm": 0.890488862991333, "learning_rate": 5.544554455445545e-05, "loss": 0.5319, "step": 771 }, { "epoch": 1.3452484742807322, "grad_norm": 0.8212575912475586, "learning_rate": 5.538730343622598e-05, "loss": 0.5329, "step": 772 }, { "epoch": 1.3469921534437663, "grad_norm": 0.860535740852356, "learning_rate": 5.5329062317996505e-05, "loss": 0.6033, "step": 773 }, { "epoch": 1.3487358326068004, "grad_norm": 0.8413981199264526, "learning_rate": 5.527082119976704e-05, "loss": 0.6142, "step": 774 }, { "epoch": 1.3504795117698343, "grad_norm": 0.8477709889411926, "learning_rate": 5.5212580081537566e-05, "loss": 0.5504, "step": 775 }, { "epoch": 1.3522231909328684, "grad_norm": 1.0181870460510254, "learning_rate": 5.515433896330809e-05, "loss": 0.6786, "step": 776 }, { "epoch": 1.3539668700959022, "grad_norm": 1.0119068622589111, "learning_rate": 5.509609784507863e-05, "loss": 0.5998, "step": 777 }, { "epoch": 1.3557105492589363, "grad_norm": 1.7611517906188965, "learning_rate": 5.503785672684916e-05, "loss": 0.8427, "step": 778 }, { "epoch": 1.3574542284219704, "grad_norm": 1.0045137405395508, "learning_rate": 5.497961560861968e-05, "loss": 0.5931, "step": 779 }, { "epoch": 1.3591979075850045, "grad_norm": 0.8112280964851379, "learning_rate": 5.492137449039022e-05, "loss": 0.5283, "step": 780 }, { "epoch": 1.3609415867480383, "grad_norm": 1.1165080070495605, "learning_rate": 5.486313337216075e-05, "loss": 0.606, "step": 781 }, { "epoch": 1.3626852659110724, "grad_norm": 1.0042351484298706, "learning_rate": 5.4804892253931275e-05, "loss": 0.6242, "step": 782 }, { "epoch": 1.3644289450741063, "grad_norm": 0.8527002930641174, "learning_rate": 5.474665113570181e-05, "loss": 0.6186, "step": 783 }, { "epoch": 1.3661726242371404, "grad_norm": 0.8763253092765808, "learning_rate": 5.4688410017472335e-05, "loss": 0.6027, "step": 784 }, { "epoch": 1.3679163034001744, "grad_norm": 1.3097522258758545, "learning_rate": 5.4630168899242876e-05, "loss": 0.6796, "step": 785 }, { "epoch": 1.3696599825632083, "grad_norm": 1.0300161838531494, "learning_rate": 5.4571927781013396e-05, "loss": 0.5767, "step": 786 }, { "epoch": 1.3714036617262424, "grad_norm": 1.2015032768249512, "learning_rate": 5.451368666278392e-05, "loss": 0.6785, "step": 787 }, { "epoch": 1.3731473408892763, "grad_norm": 1.1480567455291748, "learning_rate": 5.445544554455446e-05, "loss": 0.6261, "step": 788 }, { "epoch": 1.3748910200523103, "grad_norm": 0.8707717061042786, "learning_rate": 5.439720442632499e-05, "loss": 0.5391, "step": 789 }, { "epoch": 1.3766346992153444, "grad_norm": 1.1118723154067993, "learning_rate": 5.433896330809552e-05, "loss": 0.6373, "step": 790 }, { "epoch": 1.3783783783783785, "grad_norm": 1.0987743139266968, "learning_rate": 5.428072218986605e-05, "loss": 0.5665, "step": 791 }, { "epoch": 1.3801220575414124, "grad_norm": 1.0254815816879272, "learning_rate": 5.422248107163658e-05, "loss": 0.6483, "step": 792 }, { "epoch": 1.3818657367044465, "grad_norm": 0.9690970182418823, "learning_rate": 5.4164239953407104e-05, "loss": 0.5321, "step": 793 }, { "epoch": 1.3836094158674803, "grad_norm": 1.0870635509490967, "learning_rate": 5.410599883517764e-05, "loss": 0.6458, "step": 794 }, { "epoch": 1.3853530950305144, "grad_norm": 0.8556700348854065, "learning_rate": 5.4047757716948165e-05, "loss": 0.4922, "step": 795 }, { "epoch": 1.3870967741935485, "grad_norm": 0.9083438515663147, "learning_rate": 5.3989516598718706e-05, "loss": 0.6044, "step": 796 }, { "epoch": 1.3888404533565823, "grad_norm": 1.061547040939331, "learning_rate": 5.393127548048923e-05, "loss": 0.6561, "step": 797 }, { "epoch": 1.3905841325196164, "grad_norm": 1.0242621898651123, "learning_rate": 5.387303436225975e-05, "loss": 0.6044, "step": 798 }, { "epoch": 1.3923278116826503, "grad_norm": 1.045034408569336, "learning_rate": 5.381479324403029e-05, "loss": 0.5674, "step": 799 }, { "epoch": 1.3940714908456844, "grad_norm": 0.9453638195991516, "learning_rate": 5.375655212580082e-05, "loss": 0.622, "step": 800 }, { "epoch": 1.3958151700087185, "grad_norm": 1.102723479270935, "learning_rate": 5.369831100757135e-05, "loss": 0.6367, "step": 801 }, { "epoch": 1.3975588491717523, "grad_norm": 1.1577692031860352, "learning_rate": 5.364006988934188e-05, "loss": 0.6502, "step": 802 }, { "epoch": 1.3993025283347864, "grad_norm": 0.8348683714866638, "learning_rate": 5.358182877111241e-05, "loss": 0.5887, "step": 803 }, { "epoch": 1.4010462074978203, "grad_norm": 0.8900251388549805, "learning_rate": 5.3523587652882934e-05, "loss": 0.5991, "step": 804 }, { "epoch": 1.4027898866608544, "grad_norm": 0.9573115706443787, "learning_rate": 5.346534653465347e-05, "loss": 0.6205, "step": 805 }, { "epoch": 1.4045335658238884, "grad_norm": 0.9346290230751038, "learning_rate": 5.3407105416423995e-05, "loss": 0.5915, "step": 806 }, { "epoch": 1.4062772449869225, "grad_norm": 0.9024628400802612, "learning_rate": 5.334886429819452e-05, "loss": 0.5335, "step": 807 }, { "epoch": 1.4080209241499564, "grad_norm": 1.236770510673523, "learning_rate": 5.329062317996506e-05, "loss": 0.6455, "step": 808 }, { "epoch": 1.4097646033129905, "grad_norm": 1.0678349733352661, "learning_rate": 5.323238206173559e-05, "loss": 0.6103, "step": 809 }, { "epoch": 1.4115082824760243, "grad_norm": 0.913006603717804, "learning_rate": 5.317414094350612e-05, "loss": 0.6245, "step": 810 }, { "epoch": 1.4132519616390584, "grad_norm": 0.8503197431564331, "learning_rate": 5.311589982527665e-05, "loss": 0.5505, "step": 811 }, { "epoch": 1.4149956408020925, "grad_norm": 1.0780833959579468, "learning_rate": 5.305765870704718e-05, "loss": 0.6162, "step": 812 }, { "epoch": 1.4167393199651264, "grad_norm": 1.2274020910263062, "learning_rate": 5.299941758881771e-05, "loss": 0.7191, "step": 813 }, { "epoch": 1.4184829991281604, "grad_norm": 0.9179590940475464, "learning_rate": 5.294117647058824e-05, "loss": 0.6499, "step": 814 }, { "epoch": 1.4202266782911943, "grad_norm": 0.857323408126831, "learning_rate": 5.2882935352358764e-05, "loss": 0.5646, "step": 815 }, { "epoch": 1.4219703574542284, "grad_norm": 0.855874240398407, "learning_rate": 5.2824694234129305e-05, "loss": 0.5894, "step": 816 }, { "epoch": 1.4237140366172625, "grad_norm": 0.821758508682251, "learning_rate": 5.2766453115899825e-05, "loss": 0.5959, "step": 817 }, { "epoch": 1.4254577157802966, "grad_norm": 1.0148370265960693, "learning_rate": 5.270821199767035e-05, "loss": 0.6145, "step": 818 }, { "epoch": 1.4272013949433304, "grad_norm": 0.8590991497039795, "learning_rate": 5.264997087944089e-05, "loss": 0.4824, "step": 819 }, { "epoch": 1.4289450741063645, "grad_norm": 0.9052860140800476, "learning_rate": 5.259172976121142e-05, "loss": 0.5862, "step": 820 }, { "epoch": 1.4306887532693984, "grad_norm": 0.9531126618385315, "learning_rate": 5.2533488642981946e-05, "loss": 0.524, "step": 821 }, { "epoch": 1.4324324324324325, "grad_norm": 0.810242772102356, "learning_rate": 5.247524752475248e-05, "loss": 0.5921, "step": 822 }, { "epoch": 1.4341761115954665, "grad_norm": 0.8108171224594116, "learning_rate": 5.241700640652301e-05, "loss": 0.5835, "step": 823 }, { "epoch": 1.4359197907585004, "grad_norm": 0.8253954648971558, "learning_rate": 5.235876528829354e-05, "loss": 0.4607, "step": 824 }, { "epoch": 1.4376634699215345, "grad_norm": 1.192109227180481, "learning_rate": 5.230052417006407e-05, "loss": 0.6639, "step": 825 }, { "epoch": 1.4394071490845683, "grad_norm": 1.0662167072296143, "learning_rate": 5.2242283051834594e-05, "loss": 0.6281, "step": 826 }, { "epoch": 1.4411508282476024, "grad_norm": 0.9822310209274292, "learning_rate": 5.2184041933605135e-05, "loss": 0.5748, "step": 827 }, { "epoch": 1.4428945074106365, "grad_norm": 0.95380038022995, "learning_rate": 5.212580081537566e-05, "loss": 0.5267, "step": 828 }, { "epoch": 1.4446381865736704, "grad_norm": 1.0933653116226196, "learning_rate": 5.206755969714618e-05, "loss": 0.611, "step": 829 }, { "epoch": 1.4463818657367045, "grad_norm": 0.9805903434753418, "learning_rate": 5.200931857891672e-05, "loss": 0.5225, "step": 830 }, { "epoch": 1.4481255448997383, "grad_norm": 0.8614153861999512, "learning_rate": 5.195107746068725e-05, "loss": 0.5642, "step": 831 }, { "epoch": 1.4498692240627724, "grad_norm": 1.034512996673584, "learning_rate": 5.1892836342457776e-05, "loss": 0.562, "step": 832 }, { "epoch": 1.4516129032258065, "grad_norm": 1.0236202478408813, "learning_rate": 5.183459522422831e-05, "loss": 0.5817, "step": 833 }, { "epoch": 1.4533565823888406, "grad_norm": 0.9380700588226318, "learning_rate": 5.177635410599884e-05, "loss": 0.5573, "step": 834 }, { "epoch": 1.4551002615518744, "grad_norm": 1.0098036527633667, "learning_rate": 5.1718112987769364e-05, "loss": 0.5618, "step": 835 }, { "epoch": 1.4568439407149085, "grad_norm": 1.0541375875473022, "learning_rate": 5.16598718695399e-05, "loss": 0.6177, "step": 836 }, { "epoch": 1.4585876198779424, "grad_norm": 1.1413558721542358, "learning_rate": 5.1601630751310424e-05, "loss": 0.664, "step": 837 }, { "epoch": 1.4603312990409765, "grad_norm": 1.1423276662826538, "learning_rate": 5.1543389633080965e-05, "loss": 0.6243, "step": 838 }, { "epoch": 1.4620749782040106, "grad_norm": 1.1503279209136963, "learning_rate": 5.148514851485149e-05, "loss": 0.6894, "step": 839 }, { "epoch": 1.4638186573670444, "grad_norm": 1.094599962234497, "learning_rate": 5.142690739662201e-05, "loss": 0.6568, "step": 840 }, { "epoch": 1.4655623365300785, "grad_norm": 1.0826157331466675, "learning_rate": 5.136866627839255e-05, "loss": 0.654, "step": 841 }, { "epoch": 1.4673060156931124, "grad_norm": 1.0165972709655762, "learning_rate": 5.131042516016308e-05, "loss": 0.6608, "step": 842 }, { "epoch": 1.4690496948561464, "grad_norm": 1.067982792854309, "learning_rate": 5.1252184041933606e-05, "loss": 0.7139, "step": 843 }, { "epoch": 1.4707933740191805, "grad_norm": 0.8677641749382019, "learning_rate": 5.119394292370414e-05, "loss": 0.5889, "step": 844 }, { "epoch": 1.4725370531822144, "grad_norm": 0.8872987031936646, "learning_rate": 5.1135701805474667e-05, "loss": 0.6242, "step": 845 }, { "epoch": 1.4742807323452485, "grad_norm": 1.0033340454101562, "learning_rate": 5.1077460687245194e-05, "loss": 0.6109, "step": 846 }, { "epoch": 1.4760244115082823, "grad_norm": 0.8829697370529175, "learning_rate": 5.101921956901573e-05, "loss": 0.5829, "step": 847 }, { "epoch": 1.4777680906713164, "grad_norm": 1.0841014385223389, "learning_rate": 5.0960978450786254e-05, "loss": 0.6169, "step": 848 }, { "epoch": 1.4795117698343505, "grad_norm": 1.0584245920181274, "learning_rate": 5.090273733255678e-05, "loss": 0.5846, "step": 849 }, { "epoch": 1.4812554489973846, "grad_norm": 1.1063461303710938, "learning_rate": 5.084449621432732e-05, "loss": 0.605, "step": 850 }, { "epoch": 1.4829991281604185, "grad_norm": 1.1246423721313477, "learning_rate": 5.078625509609785e-05, "loss": 0.6769, "step": 851 }, { "epoch": 1.4847428073234525, "grad_norm": 1.0741651058197021, "learning_rate": 5.072801397786838e-05, "loss": 0.6472, "step": 852 }, { "epoch": 1.4864864864864864, "grad_norm": 1.0448821783065796, "learning_rate": 5.066977285963891e-05, "loss": 0.5997, "step": 853 }, { "epoch": 1.4882301656495205, "grad_norm": 0.9692683815956116, "learning_rate": 5.0611531741409436e-05, "loss": 0.5829, "step": 854 }, { "epoch": 1.4899738448125546, "grad_norm": 1.2053732872009277, "learning_rate": 5.055329062317997e-05, "loss": 0.5891, "step": 855 }, { "epoch": 1.4917175239755884, "grad_norm": 0.8290640115737915, "learning_rate": 5.0495049504950497e-05, "loss": 0.563, "step": 856 }, { "epoch": 1.4934612031386225, "grad_norm": 0.9351638555526733, "learning_rate": 5.0436808386721023e-05, "loss": 0.5749, "step": 857 }, { "epoch": 1.4952048823016564, "grad_norm": 1.1534795761108398, "learning_rate": 5.0378567268491564e-05, "loss": 0.6954, "step": 858 }, { "epoch": 1.4969485614646905, "grad_norm": 1.0583575963974, "learning_rate": 5.0320326150262084e-05, "loss": 0.6153, "step": 859 }, { "epoch": 1.4986922406277245, "grad_norm": 0.8083314895629883, "learning_rate": 5.026208503203261e-05, "loss": 0.5936, "step": 860 }, { "epoch": 1.5004359197907586, "grad_norm": 0.8697086572647095, "learning_rate": 5.020384391380315e-05, "loss": 0.6083, "step": 861 }, { "epoch": 1.5021795989537925, "grad_norm": 0.9142206311225891, "learning_rate": 5.014560279557368e-05, "loss": 0.5515, "step": 862 }, { "epoch": 1.5039232781168264, "grad_norm": 1.350389003753662, "learning_rate": 5.0087361677344205e-05, "loss": 0.686, "step": 863 }, { "epoch": 1.5056669572798604, "grad_norm": 1.1459786891937256, "learning_rate": 5.002912055911474e-05, "loss": 0.6622, "step": 864 }, { "epoch": 1.5074106364428945, "grad_norm": 1.2103317975997925, "learning_rate": 4.9970879440885266e-05, "loss": 0.6399, "step": 865 }, { "epoch": 1.5091543156059286, "grad_norm": 1.1439549922943115, "learning_rate": 4.99126383226558e-05, "loss": 0.6023, "step": 866 }, { "epoch": 1.5108979947689625, "grad_norm": 1.131710410118103, "learning_rate": 4.9854397204426326e-05, "loss": 0.6812, "step": 867 }, { "epoch": 1.5126416739319966, "grad_norm": 1.0307129621505737, "learning_rate": 4.979615608619686e-05, "loss": 0.6779, "step": 868 }, { "epoch": 1.5143853530950304, "grad_norm": 1.2086282968521118, "learning_rate": 4.973791496796739e-05, "loss": 0.6819, "step": 869 }, { "epoch": 1.5161290322580645, "grad_norm": 1.0514662265777588, "learning_rate": 4.967967384973792e-05, "loss": 0.6824, "step": 870 }, { "epoch": 1.5178727114210986, "grad_norm": 1.1544339656829834, "learning_rate": 4.962143273150845e-05, "loss": 0.6109, "step": 871 }, { "epoch": 1.5196163905841327, "grad_norm": 0.8093773722648621, "learning_rate": 4.9563191613278975e-05, "loss": 0.5572, "step": 872 }, { "epoch": 1.5213600697471665, "grad_norm": 0.755882978439331, "learning_rate": 4.950495049504951e-05, "loss": 0.5656, "step": 873 }, { "epoch": 1.5231037489102004, "grad_norm": 0.9053236842155457, "learning_rate": 4.9446709376820035e-05, "loss": 0.5043, "step": 874 }, { "epoch": 1.5248474280732345, "grad_norm": 1.0242643356323242, "learning_rate": 4.938846825859057e-05, "loss": 0.5939, "step": 875 }, { "epoch": 1.5265911072362686, "grad_norm": 1.223098635673523, "learning_rate": 4.9330227140361096e-05, "loss": 0.6364, "step": 876 }, { "epoch": 1.5283347863993026, "grad_norm": 1.1147385835647583, "learning_rate": 4.927198602213163e-05, "loss": 0.5969, "step": 877 }, { "epoch": 1.5300784655623365, "grad_norm": 0.9635611176490784, "learning_rate": 4.9213744903902156e-05, "loss": 0.6202, "step": 878 }, { "epoch": 1.5318221447253704, "grad_norm": 1.0552377700805664, "learning_rate": 4.915550378567268e-05, "loss": 0.5682, "step": 879 }, { "epoch": 1.5335658238884045, "grad_norm": 1.242564082145691, "learning_rate": 4.909726266744322e-05, "loss": 0.6821, "step": 880 }, { "epoch": 1.5353095030514385, "grad_norm": 0.8801543712615967, "learning_rate": 4.903902154921375e-05, "loss": 0.5447, "step": 881 }, { "epoch": 1.5370531822144726, "grad_norm": 0.8937097787857056, "learning_rate": 4.898078043098428e-05, "loss": 0.4954, "step": 882 }, { "epoch": 1.5387968613775065, "grad_norm": 1.2840442657470703, "learning_rate": 4.8922539312754804e-05, "loss": 0.6698, "step": 883 }, { "epoch": 1.5405405405405406, "grad_norm": 1.0216811895370483, "learning_rate": 4.886429819452534e-05, "loss": 0.6506, "step": 884 }, { "epoch": 1.5422842197035744, "grad_norm": 1.0105196237564087, "learning_rate": 4.880605707629587e-05, "loss": 0.4723, "step": 885 }, { "epoch": 1.5440278988666085, "grad_norm": 1.0890260934829712, "learning_rate": 4.874781595806639e-05, "loss": 0.6357, "step": 886 }, { "epoch": 1.5457715780296426, "grad_norm": 1.0534813404083252, "learning_rate": 4.8689574839836926e-05, "loss": 0.6011, "step": 887 }, { "epoch": 1.5475152571926767, "grad_norm": 0.9236336946487427, "learning_rate": 4.863133372160746e-05, "loss": 0.5301, "step": 888 }, { "epoch": 1.5492589363557105, "grad_norm": 1.2279088497161865, "learning_rate": 4.857309260337799e-05, "loss": 0.7085, "step": 889 }, { "epoch": 1.5510026155187444, "grad_norm": 1.1269721984863281, "learning_rate": 4.851485148514851e-05, "loss": 0.6385, "step": 890 }, { "epoch": 1.5527462946817785, "grad_norm": 0.9550584554672241, "learning_rate": 4.845661036691905e-05, "loss": 0.5302, "step": 891 }, { "epoch": 1.5544899738448126, "grad_norm": 1.1656315326690674, "learning_rate": 4.839836924868958e-05, "loss": 0.6072, "step": 892 }, { "epoch": 1.5562336530078467, "grad_norm": 0.9326116442680359, "learning_rate": 4.834012813046011e-05, "loss": 0.6195, "step": 893 }, { "epoch": 1.5579773321708805, "grad_norm": 0.8710398077964783, "learning_rate": 4.8281887012230634e-05, "loss": 0.5506, "step": 894 }, { "epoch": 1.5597210113339146, "grad_norm": 1.0874861478805542, "learning_rate": 4.822364589400117e-05, "loss": 0.5958, "step": 895 }, { "epoch": 1.5614646904969485, "grad_norm": 0.9253178238868713, "learning_rate": 4.81654047757717e-05, "loss": 0.5823, "step": 896 }, { "epoch": 1.5632083696599826, "grad_norm": 0.9054164290428162, "learning_rate": 4.810716365754223e-05, "loss": 0.567, "step": 897 }, { "epoch": 1.5649520488230166, "grad_norm": 1.00960373878479, "learning_rate": 4.8048922539312756e-05, "loss": 0.6659, "step": 898 }, { "epoch": 1.5666957279860507, "grad_norm": 0.9400368332862854, "learning_rate": 4.799068142108329e-05, "loss": 0.5804, "step": 899 }, { "epoch": 1.5684394071490846, "grad_norm": 1.0530152320861816, "learning_rate": 4.7932440302853816e-05, "loss": 0.5402, "step": 900 }, { "epoch": 1.5701830863121184, "grad_norm": 1.1739284992218018, "learning_rate": 4.787419918462434e-05, "loss": 0.632, "step": 901 }, { "epoch": 1.5719267654751525, "grad_norm": 0.8561078906059265, "learning_rate": 4.781595806639488e-05, "loss": 0.5992, "step": 902 }, { "epoch": 1.5736704446381866, "grad_norm": 0.9941346049308777, "learning_rate": 4.775771694816541e-05, "loss": 0.5713, "step": 903 }, { "epoch": 1.5754141238012207, "grad_norm": 1.2381514310836792, "learning_rate": 4.769947582993594e-05, "loss": 0.6579, "step": 904 }, { "epoch": 1.5771578029642546, "grad_norm": 1.022434949874878, "learning_rate": 4.7641234711706464e-05, "loss": 0.6222, "step": 905 }, { "epoch": 1.5789014821272884, "grad_norm": 1.0039677619934082, "learning_rate": 4.7582993593477e-05, "loss": 0.5498, "step": 906 }, { "epoch": 1.5806451612903225, "grad_norm": 0.8749232888221741, "learning_rate": 4.7524752475247525e-05, "loss": 0.4526, "step": 907 }, { "epoch": 1.5823888404533566, "grad_norm": 1.1878068447113037, "learning_rate": 4.746651135701806e-05, "loss": 0.6571, "step": 908 }, { "epoch": 1.5841325196163907, "grad_norm": 1.1146676540374756, "learning_rate": 4.7408270238788586e-05, "loss": 0.5674, "step": 909 }, { "epoch": 1.5858761987794245, "grad_norm": 0.9401254057884216, "learning_rate": 4.735002912055912e-05, "loss": 0.5807, "step": 910 }, { "epoch": 1.5876198779424586, "grad_norm": 0.8749872446060181, "learning_rate": 4.7291788002329646e-05, "loss": 0.5809, "step": 911 }, { "epoch": 1.5893635571054925, "grad_norm": 1.2300995588302612, "learning_rate": 4.723354688410018e-05, "loss": 0.6622, "step": 912 }, { "epoch": 1.5911072362685266, "grad_norm": 1.0274070501327515, "learning_rate": 4.717530576587071e-05, "loss": 0.5691, "step": 913 }, { "epoch": 1.5928509154315607, "grad_norm": 0.9161589741706848, "learning_rate": 4.7117064647641234e-05, "loss": 0.5158, "step": 914 }, { "epoch": 1.5945945945945947, "grad_norm": 1.1679699420928955, "learning_rate": 4.705882352941177e-05, "loss": 0.6338, "step": 915 }, { "epoch": 1.5963382737576286, "grad_norm": 1.0395523309707642, "learning_rate": 4.70005824111823e-05, "loss": 0.635, "step": 916 }, { "epoch": 1.5980819529206625, "grad_norm": 1.0967618227005005, "learning_rate": 4.694234129295283e-05, "loss": 0.6288, "step": 917 }, { "epoch": 1.5998256320836965, "grad_norm": 0.9654198884963989, "learning_rate": 4.6884100174723355e-05, "loss": 0.6093, "step": 918 }, { "epoch": 1.6015693112467306, "grad_norm": 1.2467604875564575, "learning_rate": 4.682585905649389e-05, "loss": 0.6724, "step": 919 }, { "epoch": 1.6033129904097647, "grad_norm": 1.0487215518951416, "learning_rate": 4.6767617938264415e-05, "loss": 0.6157, "step": 920 }, { "epoch": 1.6050566695727986, "grad_norm": 1.0435789823532104, "learning_rate": 4.670937682003494e-05, "loss": 0.6448, "step": 921 }, { "epoch": 1.6068003487358327, "grad_norm": 0.8733755350112915, "learning_rate": 4.6651135701805476e-05, "loss": 0.5586, "step": 922 }, { "epoch": 1.6085440278988665, "grad_norm": 0.9670316576957703, "learning_rate": 4.659289458357601e-05, "loss": 0.6312, "step": 923 }, { "epoch": 1.6102877070619006, "grad_norm": 0.7611584663391113, "learning_rate": 4.653465346534654e-05, "loss": 0.5538, "step": 924 }, { "epoch": 1.6120313862249347, "grad_norm": 1.0990899801254272, "learning_rate": 4.6476412347117064e-05, "loss": 0.6561, "step": 925 }, { "epoch": 1.6137750653879688, "grad_norm": 0.916222333908081, "learning_rate": 4.64181712288876e-05, "loss": 0.5678, "step": 926 }, { "epoch": 1.6155187445510026, "grad_norm": 1.0889514684677124, "learning_rate": 4.635993011065813e-05, "loss": 0.6508, "step": 927 }, { "epoch": 1.6172624237140365, "grad_norm": 0.9163194894790649, "learning_rate": 4.630168899242866e-05, "loss": 0.6221, "step": 928 }, { "epoch": 1.6190061028770706, "grad_norm": 1.088828682899475, "learning_rate": 4.6243447874199185e-05, "loss": 0.6195, "step": 929 }, { "epoch": 1.6207497820401047, "grad_norm": 1.0433712005615234, "learning_rate": 4.618520675596972e-05, "loss": 0.635, "step": 930 }, { "epoch": 1.6224934612031388, "grad_norm": 0.8921671509742737, "learning_rate": 4.612696563774025e-05, "loss": 0.6373, "step": 931 }, { "epoch": 1.6242371403661726, "grad_norm": 0.8621225357055664, "learning_rate": 4.606872451951077e-05, "loss": 0.5657, "step": 932 }, { "epoch": 1.6259808195292065, "grad_norm": 1.3884036540985107, "learning_rate": 4.6010483401281306e-05, "loss": 0.7272, "step": 933 }, { "epoch": 1.6277244986922406, "grad_norm": 0.8245130777359009, "learning_rate": 4.595224228305184e-05, "loss": 0.5898, "step": 934 }, { "epoch": 1.6294681778552746, "grad_norm": 0.9971787929534912, "learning_rate": 4.5894001164822367e-05, "loss": 0.6567, "step": 935 }, { "epoch": 1.6312118570183087, "grad_norm": 0.8768223524093628, "learning_rate": 4.5835760046592894e-05, "loss": 0.5588, "step": 936 }, { "epoch": 1.6329555361813426, "grad_norm": 0.8512053489685059, "learning_rate": 4.577751892836343e-05, "loss": 0.5339, "step": 937 }, { "epoch": 1.6346992153443767, "grad_norm": 1.1787939071655273, "learning_rate": 4.571927781013396e-05, "loss": 0.6241, "step": 938 }, { "epoch": 1.6364428945074105, "grad_norm": 0.9333083629608154, "learning_rate": 4.566103669190449e-05, "loss": 0.6495, "step": 939 }, { "epoch": 1.6381865736704446, "grad_norm": 0.8357792496681213, "learning_rate": 4.5602795573675015e-05, "loss": 0.5418, "step": 940 }, { "epoch": 1.6399302528334787, "grad_norm": 0.955433189868927, "learning_rate": 4.554455445544555e-05, "loss": 0.6191, "step": 941 }, { "epoch": 1.6416739319965128, "grad_norm": 1.0885087251663208, "learning_rate": 4.5486313337216075e-05, "loss": 0.6174, "step": 942 }, { "epoch": 1.6434176111595467, "grad_norm": 0.9534031748771667, "learning_rate": 4.542807221898661e-05, "loss": 0.59, "step": 943 }, { "epoch": 1.6451612903225805, "grad_norm": 0.9040201306343079, "learning_rate": 4.5369831100757136e-05, "loss": 0.6021, "step": 944 }, { "epoch": 1.6469049694856146, "grad_norm": 1.0734461545944214, "learning_rate": 4.531158998252767e-05, "loss": 0.637, "step": 945 }, { "epoch": 1.6486486486486487, "grad_norm": 0.991676390171051, "learning_rate": 4.5253348864298197e-05, "loss": 0.6015, "step": 946 }, { "epoch": 1.6503923278116828, "grad_norm": 0.9894969463348389, "learning_rate": 4.5195107746068723e-05, "loss": 0.6297, "step": 947 }, { "epoch": 1.6521360069747166, "grad_norm": 0.9115866422653198, "learning_rate": 4.513686662783926e-05, "loss": 0.5611, "step": 948 }, { "epoch": 1.6538796861377505, "grad_norm": 0.9328036904335022, "learning_rate": 4.5078625509609784e-05, "loss": 0.5401, "step": 949 }, { "epoch": 1.6556233653007846, "grad_norm": 1.0049054622650146, "learning_rate": 4.502038439138032e-05, "loss": 0.6031, "step": 950 }, { "epoch": 1.6573670444638187, "grad_norm": 1.1159324645996094, "learning_rate": 4.4962143273150845e-05, "loss": 0.668, "step": 951 }, { "epoch": 1.6591107236268527, "grad_norm": 0.7993686199188232, "learning_rate": 4.490390215492138e-05, "loss": 0.5124, "step": 952 }, { "epoch": 1.6608544027898866, "grad_norm": 0.9533082246780396, "learning_rate": 4.4845661036691905e-05, "loss": 0.5648, "step": 953 }, { "epoch": 1.6625980819529207, "grad_norm": 1.1181129217147827, "learning_rate": 4.478741991846244e-05, "loss": 0.6671, "step": 954 }, { "epoch": 1.6643417611159546, "grad_norm": 1.1271164417266846, "learning_rate": 4.4729178800232966e-05, "loss": 0.6597, "step": 955 }, { "epoch": 1.6660854402789886, "grad_norm": 0.846265971660614, "learning_rate": 4.467093768200349e-05, "loss": 0.5183, "step": 956 }, { "epoch": 1.6678291194420227, "grad_norm": 1.0320335626602173, "learning_rate": 4.4612696563774026e-05, "loss": 0.6304, "step": 957 }, { "epoch": 1.6695727986050568, "grad_norm": 1.1746759414672852, "learning_rate": 4.455445544554456e-05, "loss": 0.6442, "step": 958 }, { "epoch": 1.6713164777680907, "grad_norm": 0.906512975692749, "learning_rate": 4.449621432731509e-05, "loss": 0.5663, "step": 959 }, { "epoch": 1.6730601569311245, "grad_norm": 1.1518769264221191, "learning_rate": 4.4437973209085614e-05, "loss": 0.6301, "step": 960 }, { "epoch": 1.6748038360941586, "grad_norm": 0.8395512104034424, "learning_rate": 4.437973209085615e-05, "loss": 0.5327, "step": 961 }, { "epoch": 1.6765475152571927, "grad_norm": 0.9801402688026428, "learning_rate": 4.432149097262668e-05, "loss": 0.5528, "step": 962 }, { "epoch": 1.6782911944202268, "grad_norm": 0.8810858726501465, "learning_rate": 4.42632498543972e-05, "loss": 0.6024, "step": 963 }, { "epoch": 1.6800348735832606, "grad_norm": 0.9912739992141724, "learning_rate": 4.4205008736167735e-05, "loss": 0.6201, "step": 964 }, { "epoch": 1.6817785527462947, "grad_norm": 1.0168144702911377, "learning_rate": 4.414676761793827e-05, "loss": 0.6525, "step": 965 }, { "epoch": 1.6835222319093286, "grad_norm": 1.3027007579803467, "learning_rate": 4.4088526499708796e-05, "loss": 0.6055, "step": 966 }, { "epoch": 1.6852659110723627, "grad_norm": 0.8893110156059265, "learning_rate": 4.403028538147932e-05, "loss": 0.6141, "step": 967 }, { "epoch": 1.6870095902353968, "grad_norm": 1.3154165744781494, "learning_rate": 4.3972044263249856e-05, "loss": 0.6735, "step": 968 }, { "epoch": 1.6887532693984308, "grad_norm": 0.9329833984375, "learning_rate": 4.391380314502039e-05, "loss": 0.5772, "step": 969 }, { "epoch": 1.6904969485614647, "grad_norm": 1.16274094581604, "learning_rate": 4.385556202679092e-05, "loss": 0.7101, "step": 970 }, { "epoch": 1.6922406277244986, "grad_norm": 1.25133216381073, "learning_rate": 4.3797320908561444e-05, "loss": 0.6264, "step": 971 }, { "epoch": 1.6939843068875327, "grad_norm": 0.9085930585861206, "learning_rate": 4.373907979033198e-05, "loss": 0.5354, "step": 972 }, { "epoch": 1.6957279860505667, "grad_norm": 0.8958626985549927, "learning_rate": 4.368083867210251e-05, "loss": 0.5965, "step": 973 }, { "epoch": 1.6974716652136008, "grad_norm": 1.011084794998169, "learning_rate": 4.362259755387303e-05, "loss": 0.6384, "step": 974 }, { "epoch": 1.6992153443766347, "grad_norm": 0.8028609752655029, "learning_rate": 4.3564356435643565e-05, "loss": 0.5599, "step": 975 }, { "epoch": 1.7009590235396685, "grad_norm": 0.9015823602676392, "learning_rate": 4.35061153174141e-05, "loss": 0.5368, "step": 976 }, { "epoch": 1.7027027027027026, "grad_norm": 1.0161769390106201, "learning_rate": 4.3447874199184626e-05, "loss": 0.5261, "step": 977 }, { "epoch": 1.7044463818657367, "grad_norm": 0.9582669734954834, "learning_rate": 4.338963308095515e-05, "loss": 0.6416, "step": 978 }, { "epoch": 1.7061900610287708, "grad_norm": 1.0464985370635986, "learning_rate": 4.3331391962725686e-05, "loss": 0.6699, "step": 979 }, { "epoch": 1.7079337401918047, "grad_norm": 1.068745493888855, "learning_rate": 4.327315084449622e-05, "loss": 0.662, "step": 980 }, { "epoch": 1.7096774193548387, "grad_norm": 0.9259888529777527, "learning_rate": 4.321490972626675e-05, "loss": 0.5909, "step": 981 }, { "epoch": 1.7114210985178726, "grad_norm": 1.1789827346801758, "learning_rate": 4.3156668608037274e-05, "loss": 0.658, "step": 982 }, { "epoch": 1.7131647776809067, "grad_norm": 0.9058331251144409, "learning_rate": 4.309842748980781e-05, "loss": 0.5665, "step": 983 }, { "epoch": 1.7149084568439408, "grad_norm": 1.0420012474060059, "learning_rate": 4.3040186371578334e-05, "loss": 0.5806, "step": 984 }, { "epoch": 1.7166521360069749, "grad_norm": 0.9794200658798218, "learning_rate": 4.298194525334887e-05, "loss": 0.5908, "step": 985 }, { "epoch": 1.7183958151700087, "grad_norm": 0.9843733906745911, "learning_rate": 4.2923704135119395e-05, "loss": 0.6491, "step": 986 }, { "epoch": 1.7201394943330426, "grad_norm": 1.0647448301315308, "learning_rate": 4.286546301688993e-05, "loss": 0.5896, "step": 987 }, { "epoch": 1.7218831734960767, "grad_norm": 1.2592899799346924, "learning_rate": 4.2807221898660456e-05, "loss": 0.7027, "step": 988 }, { "epoch": 1.7236268526591108, "grad_norm": 1.0068224668502808, "learning_rate": 4.274898078043099e-05, "loss": 0.6344, "step": 989 }, { "epoch": 1.7253705318221448, "grad_norm": 1.0184495449066162, "learning_rate": 4.2690739662201516e-05, "loss": 0.5938, "step": 990 }, { "epoch": 1.7271142109851787, "grad_norm": 0.9618072509765625, "learning_rate": 4.263249854397204e-05, "loss": 0.5815, "step": 991 }, { "epoch": 1.7288578901482128, "grad_norm": 0.8471362590789795, "learning_rate": 4.257425742574258e-05, "loss": 0.4991, "step": 992 }, { "epoch": 1.7306015693112466, "grad_norm": 1.6490659713745117, "learning_rate": 4.2516016307513104e-05, "loss": 0.7993, "step": 993 }, { "epoch": 1.7323452484742807, "grad_norm": 0.8597069382667542, "learning_rate": 4.245777518928364e-05, "loss": 0.5737, "step": 994 }, { "epoch": 1.7340889276373148, "grad_norm": 0.9941847920417786, "learning_rate": 4.2399534071054164e-05, "loss": 0.5611, "step": 995 }, { "epoch": 1.735832606800349, "grad_norm": 1.1688414812088013, "learning_rate": 4.23412929528247e-05, "loss": 0.6852, "step": 996 }, { "epoch": 1.7375762859633828, "grad_norm": 1.3040813207626343, "learning_rate": 4.2283051834595225e-05, "loss": 0.6629, "step": 997 }, { "epoch": 1.7393199651264166, "grad_norm": 1.154449701309204, "learning_rate": 4.222481071636575e-05, "loss": 0.5759, "step": 998 }, { "epoch": 1.7410636442894507, "grad_norm": 1.0046051740646362, "learning_rate": 4.2166569598136286e-05, "loss": 0.5661, "step": 999 }, { "epoch": 1.7428073234524848, "grad_norm": 0.8867891430854797, "learning_rate": 4.210832847990682e-05, "loss": 0.5719, "step": 1000 }, { "epoch": 1.7445510026155189, "grad_norm": 1.0042457580566406, "learning_rate": 4.2050087361677346e-05, "loss": 0.6058, "step": 1001 }, { "epoch": 1.7462946817785527, "grad_norm": 0.9062073826789856, "learning_rate": 4.199184624344787e-05, "loss": 0.589, "step": 1002 }, { "epoch": 1.7480383609415866, "grad_norm": 1.0002449750900269, "learning_rate": 4.193360512521841e-05, "loss": 0.6012, "step": 1003 }, { "epoch": 1.7497820401046207, "grad_norm": 1.0154104232788086, "learning_rate": 4.187536400698894e-05, "loss": 0.6204, "step": 1004 }, { "epoch": 1.7515257192676548, "grad_norm": 1.407607078552246, "learning_rate": 4.181712288875946e-05, "loss": 0.6214, "step": 1005 }, { "epoch": 1.7532693984306889, "grad_norm": 0.9564329385757446, "learning_rate": 4.1758881770529994e-05, "loss": 0.5653, "step": 1006 }, { "epoch": 1.7550130775937227, "grad_norm": 1.1419034004211426, "learning_rate": 4.170064065230053e-05, "loss": 0.6337, "step": 1007 }, { "epoch": 1.7567567567567568, "grad_norm": 0.854593813419342, "learning_rate": 4.1642399534071055e-05, "loss": 0.5091, "step": 1008 }, { "epoch": 1.7585004359197907, "grad_norm": 1.0572216510772705, "learning_rate": 4.158415841584158e-05, "loss": 0.6644, "step": 1009 }, { "epoch": 1.7602441150828247, "grad_norm": 1.0837799310684204, "learning_rate": 4.1525917297612115e-05, "loss": 0.6062, "step": 1010 }, { "epoch": 1.7619877942458588, "grad_norm": 1.1744282245635986, "learning_rate": 4.146767617938265e-05, "loss": 0.6456, "step": 1011 }, { "epoch": 1.763731473408893, "grad_norm": 1.1255683898925781, "learning_rate": 4.1409435061153176e-05, "loss": 0.5764, "step": 1012 }, { "epoch": 1.7654751525719268, "grad_norm": 1.1338509321212769, "learning_rate": 4.13511939429237e-05, "loss": 0.6711, "step": 1013 }, { "epoch": 1.7672188317349606, "grad_norm": 0.9756821990013123, "learning_rate": 4.129295282469424e-05, "loss": 0.5275, "step": 1014 }, { "epoch": 1.7689625108979947, "grad_norm": 0.9416114091873169, "learning_rate": 4.123471170646477e-05, "loss": 0.6482, "step": 1015 }, { "epoch": 1.7707061900610288, "grad_norm": 1.3135439157485962, "learning_rate": 4.11764705882353e-05, "loss": 0.7146, "step": 1016 }, { "epoch": 1.772449869224063, "grad_norm": 1.4198801517486572, "learning_rate": 4.1118229470005824e-05, "loss": 0.6292, "step": 1017 }, { "epoch": 1.7741935483870968, "grad_norm": 0.9636615514755249, "learning_rate": 4.105998835177636e-05, "loss": 0.6141, "step": 1018 }, { "epoch": 1.7759372275501306, "grad_norm": 1.2508543729782104, "learning_rate": 4.1001747233546885e-05, "loss": 0.6284, "step": 1019 }, { "epoch": 1.7776809067131647, "grad_norm": 1.0495846271514893, "learning_rate": 4.094350611531741e-05, "loss": 0.6624, "step": 1020 }, { "epoch": 1.7794245858761988, "grad_norm": 1.2338682413101196, "learning_rate": 4.0885264997087945e-05, "loss": 0.6993, "step": 1021 }, { "epoch": 1.7811682650392329, "grad_norm": 1.054936170578003, "learning_rate": 4.082702387885848e-05, "loss": 0.598, "step": 1022 }, { "epoch": 1.7829119442022667, "grad_norm": 1.1435438394546509, "learning_rate": 4.0768782760629006e-05, "loss": 0.6107, "step": 1023 }, { "epoch": 1.7846556233653008, "grad_norm": 0.8226123452186584, "learning_rate": 4.071054164239953e-05, "loss": 0.5278, "step": 1024 }, { "epoch": 1.7863993025283347, "grad_norm": 0.9932762384414673, "learning_rate": 4.0652300524170067e-05, "loss": 0.6409, "step": 1025 }, { "epoch": 1.7881429816913688, "grad_norm": 1.5950731039047241, "learning_rate": 4.05940594059406e-05, "loss": 0.7617, "step": 1026 }, { "epoch": 1.7898866608544028, "grad_norm": 1.0818437337875366, "learning_rate": 4.053581828771113e-05, "loss": 0.593, "step": 1027 }, { "epoch": 1.791630340017437, "grad_norm": 1.123781681060791, "learning_rate": 4.0477577169481654e-05, "loss": 0.6171, "step": 1028 }, { "epoch": 1.7933740191804708, "grad_norm": 0.9908881187438965, "learning_rate": 4.041933605125219e-05, "loss": 0.6068, "step": 1029 }, { "epoch": 1.7951176983435047, "grad_norm": 1.070958137512207, "learning_rate": 4.0361094933022715e-05, "loss": 0.635, "step": 1030 }, { "epoch": 1.7968613775065387, "grad_norm": 1.155300498008728, "learning_rate": 4.030285381479325e-05, "loss": 0.6085, "step": 1031 }, { "epoch": 1.7986050566695728, "grad_norm": 0.9531669020652771, "learning_rate": 4.0244612696563775e-05, "loss": 0.5912, "step": 1032 }, { "epoch": 1.800348735832607, "grad_norm": 1.2634222507476807, "learning_rate": 4.018637157833431e-05, "loss": 0.7458, "step": 1033 }, { "epoch": 1.8020924149956408, "grad_norm": 1.150205373764038, "learning_rate": 4.0128130460104836e-05, "loss": 0.6122, "step": 1034 }, { "epoch": 1.8038360941586749, "grad_norm": 0.8902502655982971, "learning_rate": 4.006988934187537e-05, "loss": 0.6286, "step": 1035 }, { "epoch": 1.8055797733217087, "grad_norm": 1.6467403173446655, "learning_rate": 4.0011648223645897e-05, "loss": 0.6543, "step": 1036 }, { "epoch": 1.8073234524847428, "grad_norm": 1.105765461921692, "learning_rate": 3.9953407105416423e-05, "loss": 0.6111, "step": 1037 }, { "epoch": 1.8090671316477769, "grad_norm": 0.9005142450332642, "learning_rate": 3.989516598718696e-05, "loss": 0.5597, "step": 1038 }, { "epoch": 1.810810810810811, "grad_norm": 1.1451780796051025, "learning_rate": 3.9836924868957484e-05, "loss": 0.6274, "step": 1039 }, { "epoch": 1.8125544899738448, "grad_norm": 1.430417537689209, "learning_rate": 3.977868375072802e-05, "loss": 0.7328, "step": 1040 }, { "epoch": 1.8142981691368787, "grad_norm": 1.1419545412063599, "learning_rate": 3.9720442632498545e-05, "loss": 0.6152, "step": 1041 }, { "epoch": 1.8160418482999128, "grad_norm": 0.9316723942756653, "learning_rate": 3.966220151426908e-05, "loss": 0.5969, "step": 1042 }, { "epoch": 1.8177855274629469, "grad_norm": 0.9070554375648499, "learning_rate": 3.9603960396039605e-05, "loss": 0.5596, "step": 1043 }, { "epoch": 1.819529206625981, "grad_norm": 1.1060988903045654, "learning_rate": 3.954571927781013e-05, "loss": 0.6309, "step": 1044 }, { "epoch": 1.8212728857890148, "grad_norm": 1.2127918004989624, "learning_rate": 3.9487478159580666e-05, "loss": 0.6687, "step": 1045 }, { "epoch": 1.8230165649520487, "grad_norm": 0.7983288168907166, "learning_rate": 3.94292370413512e-05, "loss": 0.5058, "step": 1046 }, { "epoch": 1.8247602441150828, "grad_norm": 1.1644128561019897, "learning_rate": 3.9370995923121726e-05, "loss": 0.5331, "step": 1047 }, { "epoch": 1.8265039232781168, "grad_norm": 1.0334031581878662, "learning_rate": 3.931275480489225e-05, "loss": 0.5985, "step": 1048 }, { "epoch": 1.828247602441151, "grad_norm": 1.161544680595398, "learning_rate": 3.925451368666279e-05, "loss": 0.6439, "step": 1049 }, { "epoch": 1.8299912816041848, "grad_norm": 0.9637786746025085, "learning_rate": 3.919627256843332e-05, "loss": 0.5437, "step": 1050 }, { "epoch": 1.8317349607672189, "grad_norm": 0.9871627688407898, "learning_rate": 3.913803145020384e-05, "loss": 0.5936, "step": 1051 }, { "epoch": 1.8334786399302527, "grad_norm": 1.0233906507492065, "learning_rate": 3.9079790331974375e-05, "loss": 0.6362, "step": 1052 }, { "epoch": 1.8352223190932868, "grad_norm": 1.0737652778625488, "learning_rate": 3.902154921374491e-05, "loss": 0.6557, "step": 1053 }, { "epoch": 1.836965998256321, "grad_norm": 0.8977177739143372, "learning_rate": 3.8963308095515435e-05, "loss": 0.5209, "step": 1054 }, { "epoch": 1.838709677419355, "grad_norm": 1.0351066589355469, "learning_rate": 3.890506697728596e-05, "loss": 0.5278, "step": 1055 }, { "epoch": 1.8404533565823888, "grad_norm": 0.9777706265449524, "learning_rate": 3.8846825859056496e-05, "loss": 0.5984, "step": 1056 }, { "epoch": 1.8421970357454227, "grad_norm": 1.2679795026779175, "learning_rate": 3.878858474082703e-05, "loss": 0.655, "step": 1057 }, { "epoch": 1.8439407149084568, "grad_norm": 1.1136138439178467, "learning_rate": 3.8730343622597556e-05, "loss": 0.6024, "step": 1058 }, { "epoch": 1.8456843940714909, "grad_norm": 0.9899002909660339, "learning_rate": 3.867210250436808e-05, "loss": 0.5656, "step": 1059 }, { "epoch": 1.847428073234525, "grad_norm": 0.9572522044181824, "learning_rate": 3.861386138613862e-05, "loss": 0.5525, "step": 1060 }, { "epoch": 1.8491717523975588, "grad_norm": 1.126739740371704, "learning_rate": 3.855562026790915e-05, "loss": 0.658, "step": 1061 }, { "epoch": 1.850915431560593, "grad_norm": 1.03981351852417, "learning_rate": 3.849737914967968e-05, "loss": 0.6163, "step": 1062 }, { "epoch": 1.8526591107236268, "grad_norm": 1.0720847845077515, "learning_rate": 3.8439138031450205e-05, "loss": 0.6902, "step": 1063 }, { "epoch": 1.8544027898866609, "grad_norm": 0.9188697338104248, "learning_rate": 3.838089691322074e-05, "loss": 0.6599, "step": 1064 }, { "epoch": 1.856146469049695, "grad_norm": 0.9899005889892578, "learning_rate": 3.8322655794991265e-05, "loss": 0.5884, "step": 1065 }, { "epoch": 1.857890148212729, "grad_norm": 0.9227075576782227, "learning_rate": 3.826441467676179e-05, "loss": 0.5886, "step": 1066 }, { "epoch": 1.8596338273757629, "grad_norm": 1.101637363433838, "learning_rate": 3.8206173558532326e-05, "loss": 0.6021, "step": 1067 }, { "epoch": 1.8613775065387967, "grad_norm": 1.0934487581253052, "learning_rate": 3.814793244030286e-05, "loss": 0.6703, "step": 1068 }, { "epoch": 1.8631211857018308, "grad_norm": 1.1993898153305054, "learning_rate": 3.8089691322073386e-05, "loss": 0.609, "step": 1069 }, { "epoch": 1.864864864864865, "grad_norm": 1.0771105289459229, "learning_rate": 3.803145020384391e-05, "loss": 0.6113, "step": 1070 }, { "epoch": 1.866608544027899, "grad_norm": 1.0189152956008911, "learning_rate": 3.797320908561445e-05, "loss": 0.5065, "step": 1071 }, { "epoch": 1.8683522231909329, "grad_norm": 1.058883786201477, "learning_rate": 3.7914967967384974e-05, "loss": 0.6028, "step": 1072 }, { "epoch": 1.8700959023539667, "grad_norm": 0.9523096084594727, "learning_rate": 3.785672684915551e-05, "loss": 0.5024, "step": 1073 }, { "epoch": 1.8718395815170008, "grad_norm": 0.9255436658859253, "learning_rate": 3.7798485730926034e-05, "loss": 0.5295, "step": 1074 }, { "epoch": 1.873583260680035, "grad_norm": 0.8374921083450317, "learning_rate": 3.774024461269657e-05, "loss": 0.5634, "step": 1075 }, { "epoch": 1.875326939843069, "grad_norm": 1.0368916988372803, "learning_rate": 3.7682003494467095e-05, "loss": 0.6785, "step": 1076 }, { "epoch": 1.8770706190061028, "grad_norm": 1.0620914697647095, "learning_rate": 3.762376237623763e-05, "loss": 0.6143, "step": 1077 }, { "epoch": 1.878814298169137, "grad_norm": 1.065775752067566, "learning_rate": 3.7565521258008156e-05, "loss": 0.5914, "step": 1078 }, { "epoch": 1.8805579773321708, "grad_norm": 1.2015265226364136, "learning_rate": 3.750728013977868e-05, "loss": 0.6553, "step": 1079 }, { "epoch": 1.8823016564952049, "grad_norm": 1.0774614810943604, "learning_rate": 3.7449039021549216e-05, "loss": 0.6195, "step": 1080 }, { "epoch": 1.884045335658239, "grad_norm": 0.8965857028961182, "learning_rate": 3.739079790331974e-05, "loss": 0.5448, "step": 1081 }, { "epoch": 1.885789014821273, "grad_norm": 0.9474054574966431, "learning_rate": 3.733255678509028e-05, "loss": 0.5837, "step": 1082 }, { "epoch": 1.887532693984307, "grad_norm": 1.0901246070861816, "learning_rate": 3.7274315666860804e-05, "loss": 0.6128, "step": 1083 }, { "epoch": 1.8892763731473408, "grad_norm": 1.0787148475646973, "learning_rate": 3.721607454863134e-05, "loss": 0.608, "step": 1084 }, { "epoch": 1.8910200523103748, "grad_norm": 1.4603540897369385, "learning_rate": 3.7157833430401864e-05, "loss": 0.7908, "step": 1085 }, { "epoch": 1.892763731473409, "grad_norm": 0.8664311170578003, "learning_rate": 3.709959231217239e-05, "loss": 0.5919, "step": 1086 }, { "epoch": 1.894507410636443, "grad_norm": 1.0567508935928345, "learning_rate": 3.7041351193942925e-05, "loss": 0.6171, "step": 1087 }, { "epoch": 1.8962510897994769, "grad_norm": 1.4106203317642212, "learning_rate": 3.698311007571346e-05, "loss": 0.6389, "step": 1088 }, { "epoch": 1.8979947689625107, "grad_norm": 1.1987777948379517, "learning_rate": 3.6924868957483986e-05, "loss": 0.578, "step": 1089 }, { "epoch": 1.8997384481255448, "grad_norm": 0.8554938435554504, "learning_rate": 3.686662783925451e-05, "loss": 0.5087, "step": 1090 }, { "epoch": 1.901482127288579, "grad_norm": 0.9362527132034302, "learning_rate": 3.6808386721025046e-05, "loss": 0.5144, "step": 1091 }, { "epoch": 1.903225806451613, "grad_norm": 1.005141019821167, "learning_rate": 3.675014560279558e-05, "loss": 0.5349, "step": 1092 }, { "epoch": 1.9049694856146469, "grad_norm": 1.028232216835022, "learning_rate": 3.66919044845661e-05, "loss": 0.5819, "step": 1093 }, { "epoch": 1.906713164777681, "grad_norm": 1.20509934425354, "learning_rate": 3.6633663366336634e-05, "loss": 0.641, "step": 1094 }, { "epoch": 1.9084568439407148, "grad_norm": 0.8655473589897156, "learning_rate": 3.657542224810717e-05, "loss": 0.5154, "step": 1095 }, { "epoch": 1.9102005231037489, "grad_norm": 1.3437831401824951, "learning_rate": 3.65171811298777e-05, "loss": 0.6923, "step": 1096 }, { "epoch": 1.911944202266783, "grad_norm": 0.9231719374656677, "learning_rate": 3.645894001164822e-05, "loss": 0.578, "step": 1097 }, { "epoch": 1.913687881429817, "grad_norm": 1.261032223701477, "learning_rate": 3.6400698893418755e-05, "loss": 0.7013, "step": 1098 }, { "epoch": 1.915431560592851, "grad_norm": 0.9766733050346375, "learning_rate": 3.634245777518929e-05, "loss": 0.5751, "step": 1099 }, { "epoch": 1.9171752397558848, "grad_norm": 1.2266024351119995, "learning_rate": 3.6284216656959815e-05, "loss": 0.6057, "step": 1100 }, { "epoch": 1.9189189189189189, "grad_norm": 1.1696077585220337, "learning_rate": 3.622597553873034e-05, "loss": 0.6484, "step": 1101 }, { "epoch": 1.920662598081953, "grad_norm": 1.1000937223434448, "learning_rate": 3.6167734420500876e-05, "loss": 0.6016, "step": 1102 }, { "epoch": 1.922406277244987, "grad_norm": 0.9984411001205444, "learning_rate": 3.610949330227141e-05, "loss": 0.4333, "step": 1103 }, { "epoch": 1.924149956408021, "grad_norm": 0.8966373205184937, "learning_rate": 3.605125218404194e-05, "loss": 0.543, "step": 1104 }, { "epoch": 1.925893635571055, "grad_norm": 0.8983555436134338, "learning_rate": 3.5993011065812464e-05, "loss": 0.5271, "step": 1105 }, { "epoch": 1.9276373147340888, "grad_norm": 0.9584195017814636, "learning_rate": 3.5934769947583e-05, "loss": 0.6682, "step": 1106 }, { "epoch": 1.929380993897123, "grad_norm": 1.068963646888733, "learning_rate": 3.5876528829353524e-05, "loss": 0.609, "step": 1107 }, { "epoch": 1.931124673060157, "grad_norm": 1.3130511045455933, "learning_rate": 3.581828771112405e-05, "loss": 0.6313, "step": 1108 }, { "epoch": 1.932868352223191, "grad_norm": 0.8249070644378662, "learning_rate": 3.5760046592894585e-05, "loss": 0.4636, "step": 1109 }, { "epoch": 1.934612031386225, "grad_norm": 0.7441235184669495, "learning_rate": 3.570180547466512e-05, "loss": 0.4658, "step": 1110 }, { "epoch": 1.9363557105492588, "grad_norm": 1.0090503692626953, "learning_rate": 3.5643564356435645e-05, "loss": 0.59, "step": 1111 }, { "epoch": 1.938099389712293, "grad_norm": 0.8836996555328369, "learning_rate": 3.558532323820617e-05, "loss": 0.5027, "step": 1112 }, { "epoch": 1.939843068875327, "grad_norm": 1.0774706602096558, "learning_rate": 3.5527082119976706e-05, "loss": 0.6221, "step": 1113 }, { "epoch": 1.941586748038361, "grad_norm": 1.0618996620178223, "learning_rate": 3.546884100174723e-05, "loss": 0.5816, "step": 1114 }, { "epoch": 1.943330427201395, "grad_norm": 1.0872408151626587, "learning_rate": 3.5410599883517767e-05, "loss": 0.644, "step": 1115 }, { "epoch": 1.9450741063644288, "grad_norm": 0.885385274887085, "learning_rate": 3.5352358765288294e-05, "loss": 0.5469, "step": 1116 }, { "epoch": 1.9468177855274629, "grad_norm": 1.1221575736999512, "learning_rate": 3.529411764705883e-05, "loss": 0.6064, "step": 1117 }, { "epoch": 1.948561464690497, "grad_norm": 1.0101392269134521, "learning_rate": 3.5235876528829354e-05, "loss": 0.5828, "step": 1118 }, { "epoch": 1.950305143853531, "grad_norm": 1.1597882509231567, "learning_rate": 3.517763541059989e-05, "loss": 0.5995, "step": 1119 }, { "epoch": 1.952048823016565, "grad_norm": 1.0847749710083008, "learning_rate": 3.5119394292370415e-05, "loss": 0.6132, "step": 1120 }, { "epoch": 1.953792502179599, "grad_norm": 0.9348943829536438, "learning_rate": 3.506115317414094e-05, "loss": 0.5861, "step": 1121 }, { "epoch": 1.9555361813426329, "grad_norm": 0.9187694787979126, "learning_rate": 3.5002912055911475e-05, "loss": 0.5091, "step": 1122 }, { "epoch": 1.957279860505667, "grad_norm": 0.9227436184883118, "learning_rate": 3.494467093768201e-05, "loss": 0.5577, "step": 1123 }, { "epoch": 1.959023539668701, "grad_norm": 1.272908091545105, "learning_rate": 3.4886429819452536e-05, "loss": 0.6257, "step": 1124 }, { "epoch": 1.960767218831735, "grad_norm": 1.1106961965560913, "learning_rate": 3.482818870122306e-05, "loss": 0.5719, "step": 1125 }, { "epoch": 1.962510897994769, "grad_norm": 1.025322437286377, "learning_rate": 3.4769947582993597e-05, "loss": 0.6082, "step": 1126 }, { "epoch": 1.9642545771578028, "grad_norm": 1.168632984161377, "learning_rate": 3.4711706464764123e-05, "loss": 0.642, "step": 1127 }, { "epoch": 1.965998256320837, "grad_norm": 0.8933599591255188, "learning_rate": 3.465346534653465e-05, "loss": 0.6507, "step": 1128 }, { "epoch": 1.967741935483871, "grad_norm": 1.257941722869873, "learning_rate": 3.4595224228305184e-05, "loss": 0.6812, "step": 1129 }, { "epoch": 1.969485614646905, "grad_norm": 0.9157400131225586, "learning_rate": 3.453698311007572e-05, "loss": 0.5409, "step": 1130 }, { "epoch": 1.971229293809939, "grad_norm": 0.9330477714538574, "learning_rate": 3.4478741991846245e-05, "loss": 0.4948, "step": 1131 }, { "epoch": 1.972972972972973, "grad_norm": 0.9494757056236267, "learning_rate": 3.442050087361677e-05, "loss": 0.6, "step": 1132 }, { "epoch": 1.974716652136007, "grad_norm": 1.0908150672912598, "learning_rate": 3.4362259755387305e-05, "loss": 0.6024, "step": 1133 }, { "epoch": 1.976460331299041, "grad_norm": 0.9528616070747375, "learning_rate": 3.430401863715784e-05, "loss": 0.6278, "step": 1134 }, { "epoch": 1.978204010462075, "grad_norm": 0.8928424715995789, "learning_rate": 3.4245777518928366e-05, "loss": 0.5704, "step": 1135 }, { "epoch": 1.9799476896251091, "grad_norm": 0.9045881032943726, "learning_rate": 3.418753640069889e-05, "loss": 0.5481, "step": 1136 }, { "epoch": 1.981691368788143, "grad_norm": 1.0025931596755981, "learning_rate": 3.4129295282469426e-05, "loss": 0.5975, "step": 1137 }, { "epoch": 1.9834350479511769, "grad_norm": 0.9942112565040588, "learning_rate": 3.407105416423996e-05, "loss": 0.6133, "step": 1138 }, { "epoch": 1.985178727114211, "grad_norm": 0.9665239453315735, "learning_rate": 3.401281304601048e-05, "loss": 0.5878, "step": 1139 }, { "epoch": 1.986922406277245, "grad_norm": 0.940213680267334, "learning_rate": 3.3954571927781014e-05, "loss": 0.5218, "step": 1140 }, { "epoch": 1.9886660854402791, "grad_norm": 1.3435883522033691, "learning_rate": 3.389633080955155e-05, "loss": 0.7076, "step": 1141 }, { "epoch": 1.990409764603313, "grad_norm": 1.149725079536438, "learning_rate": 3.3838089691322075e-05, "loss": 0.6409, "step": 1142 }, { "epoch": 1.9921534437663468, "grad_norm": 1.075644850730896, "learning_rate": 3.37798485730926e-05, "loss": 0.5814, "step": 1143 }, { "epoch": 1.993897122929381, "grad_norm": 1.1070321798324585, "learning_rate": 3.3721607454863135e-05, "loss": 0.6027, "step": 1144 }, { "epoch": 1.995640802092415, "grad_norm": 1.2482308149337769, "learning_rate": 3.366336633663367e-05, "loss": 0.6142, "step": 1145 }, { "epoch": 1.997384481255449, "grad_norm": 1.0762617588043213, "learning_rate": 3.3605125218404196e-05, "loss": 0.5883, "step": 1146 }, { "epoch": 1.999128160418483, "grad_norm": 0.9205142855644226, "learning_rate": 3.354688410017472e-05, "loss": 0.5783, "step": 1147 }, { "epoch": 2.0, "grad_norm": 1.7877562046051025, "learning_rate": 3.3488642981945256e-05, "loss": 0.6505, "step": 1148 }, { "epoch": 2.001743679163034, "grad_norm": 0.8448851108551025, "learning_rate": 3.343040186371578e-05, "loss": 0.3625, "step": 1149 }, { "epoch": 2.003487358326068, "grad_norm": 1.012213945388794, "learning_rate": 3.337216074548632e-05, "loss": 0.4012, "step": 1150 }, { "epoch": 2.005231037489102, "grad_norm": 1.0464146137237549, "learning_rate": 3.3313919627256844e-05, "loss": 0.4773, "step": 1151 }, { "epoch": 2.006974716652136, "grad_norm": 1.0050945281982422, "learning_rate": 3.325567850902738e-05, "loss": 0.4162, "step": 1152 }, { "epoch": 2.00871839581517, "grad_norm": 0.8409005403518677, "learning_rate": 3.3197437390797905e-05, "loss": 0.3635, "step": 1153 }, { "epoch": 2.010462074978204, "grad_norm": 0.8384494185447693, "learning_rate": 3.313919627256843e-05, "loss": 0.3345, "step": 1154 }, { "epoch": 2.012205754141238, "grad_norm": 0.9382221102714539, "learning_rate": 3.3080955154338965e-05, "loss": 0.36, "step": 1155 }, { "epoch": 2.0139494333042722, "grad_norm": 0.7995953559875488, "learning_rate": 3.302271403610949e-05, "loss": 0.3651, "step": 1156 }, { "epoch": 2.015693112467306, "grad_norm": 1.0759882926940918, "learning_rate": 3.2964472917880026e-05, "loss": 0.3849, "step": 1157 }, { "epoch": 2.01743679163034, "grad_norm": 1.0657978057861328, "learning_rate": 3.290623179965055e-05, "loss": 0.3318, "step": 1158 }, { "epoch": 2.019180470793374, "grad_norm": 1.1625480651855469, "learning_rate": 3.2847990681421086e-05, "loss": 0.3554, "step": 1159 }, { "epoch": 2.020924149956408, "grad_norm": 1.1341931819915771, "learning_rate": 3.278974956319161e-05, "loss": 0.3316, "step": 1160 }, { "epoch": 2.022667829119442, "grad_norm": 1.2590667009353638, "learning_rate": 3.273150844496215e-05, "loss": 0.3683, "step": 1161 }, { "epoch": 2.024411508282476, "grad_norm": 1.106141448020935, "learning_rate": 3.2673267326732674e-05, "loss": 0.3807, "step": 1162 }, { "epoch": 2.02615518744551, "grad_norm": 2.0934345722198486, "learning_rate": 3.26150262085032e-05, "loss": 0.3859, "step": 1163 }, { "epoch": 2.027898866608544, "grad_norm": 1.0358415842056274, "learning_rate": 3.2556785090273734e-05, "loss": 0.3146, "step": 1164 }, { "epoch": 2.029642545771578, "grad_norm": 1.1213395595550537, "learning_rate": 3.249854397204427e-05, "loss": 0.3478, "step": 1165 }, { "epoch": 2.031386224934612, "grad_norm": 1.1824243068695068, "learning_rate": 3.2440302853814795e-05, "loss": 0.3774, "step": 1166 }, { "epoch": 2.033129904097646, "grad_norm": 1.2700526714324951, "learning_rate": 3.238206173558532e-05, "loss": 0.3594, "step": 1167 }, { "epoch": 2.03487358326068, "grad_norm": 1.0082933902740479, "learning_rate": 3.2323820617355856e-05, "loss": 0.309, "step": 1168 }, { "epoch": 2.036617262423714, "grad_norm": 1.037778377532959, "learning_rate": 3.226557949912639e-05, "loss": 0.3544, "step": 1169 }, { "epoch": 2.038360941586748, "grad_norm": 0.9230548143386841, "learning_rate": 3.220733838089691e-05, "loss": 0.3277, "step": 1170 }, { "epoch": 2.040104620749782, "grad_norm": 1.1100610494613647, "learning_rate": 3.214909726266744e-05, "loss": 0.409, "step": 1171 }, { "epoch": 2.0418482999128162, "grad_norm": 1.0826786756515503, "learning_rate": 3.209085614443798e-05, "loss": 0.39, "step": 1172 }, { "epoch": 2.04359197907585, "grad_norm": 0.9500569105148315, "learning_rate": 3.2032615026208504e-05, "loss": 0.3301, "step": 1173 }, { "epoch": 2.045335658238884, "grad_norm": 1.2834945917129517, "learning_rate": 3.197437390797903e-05, "loss": 0.4221, "step": 1174 }, { "epoch": 2.047079337401918, "grad_norm": 0.910670280456543, "learning_rate": 3.1916132789749564e-05, "loss": 0.3271, "step": 1175 }, { "epoch": 2.048823016564952, "grad_norm": 0.9778887033462524, "learning_rate": 3.18578916715201e-05, "loss": 0.3683, "step": 1176 }, { "epoch": 2.050566695727986, "grad_norm": 1.080529808998108, "learning_rate": 3.1799650553290625e-05, "loss": 0.4065, "step": 1177 }, { "epoch": 2.05231037489102, "grad_norm": 1.022584080696106, "learning_rate": 3.174140943506115e-05, "loss": 0.4219, "step": 1178 }, { "epoch": 2.054054054054054, "grad_norm": 1.0476068258285522, "learning_rate": 3.1683168316831686e-05, "loss": 0.4418, "step": 1179 }, { "epoch": 2.055797733217088, "grad_norm": 0.9923853278160095, "learning_rate": 3.162492719860222e-05, "loss": 0.4036, "step": 1180 }, { "epoch": 2.057541412380122, "grad_norm": 1.0238527059555054, "learning_rate": 3.156668608037274e-05, "loss": 0.3713, "step": 1181 }, { "epoch": 2.059285091543156, "grad_norm": 0.9871208071708679, "learning_rate": 3.150844496214327e-05, "loss": 0.3284, "step": 1182 }, { "epoch": 2.06102877070619, "grad_norm": 1.0775970220565796, "learning_rate": 3.145020384391381e-05, "loss": 0.388, "step": 1183 }, { "epoch": 2.062772449869224, "grad_norm": 1.069983959197998, "learning_rate": 3.139196272568434e-05, "loss": 0.3401, "step": 1184 }, { "epoch": 2.064516129032258, "grad_norm": 0.8219161629676819, "learning_rate": 3.133372160745486e-05, "loss": 0.3037, "step": 1185 }, { "epoch": 2.066259808195292, "grad_norm": 1.0656706094741821, "learning_rate": 3.1275480489225394e-05, "loss": 0.3662, "step": 1186 }, { "epoch": 2.068003487358326, "grad_norm": 1.2709523439407349, "learning_rate": 3.121723937099593e-05, "loss": 0.3555, "step": 1187 }, { "epoch": 2.0697471665213603, "grad_norm": 1.2574925422668457, "learning_rate": 3.1158998252766455e-05, "loss": 0.3696, "step": 1188 }, { "epoch": 2.071490845684394, "grad_norm": 1.1721384525299072, "learning_rate": 3.110075713453698e-05, "loss": 0.3745, "step": 1189 }, { "epoch": 2.073234524847428, "grad_norm": 1.0732803344726562, "learning_rate": 3.1042516016307515e-05, "loss": 0.352, "step": 1190 }, { "epoch": 2.074978204010462, "grad_norm": 1.0160266160964966, "learning_rate": 3.098427489807805e-05, "loss": 0.3205, "step": 1191 }, { "epoch": 2.076721883173496, "grad_norm": 1.1842966079711914, "learning_rate": 3.0926033779848576e-05, "loss": 0.4079, "step": 1192 }, { "epoch": 2.0784655623365302, "grad_norm": 1.0546547174453735, "learning_rate": 3.08677926616191e-05, "loss": 0.3238, "step": 1193 }, { "epoch": 2.080209241499564, "grad_norm": 1.548978567123413, "learning_rate": 3.080955154338964e-05, "loss": 0.4246, "step": 1194 }, { "epoch": 2.081952920662598, "grad_norm": 0.8603331446647644, "learning_rate": 3.0751310425160164e-05, "loss": 0.3166, "step": 1195 }, { "epoch": 2.083696599825632, "grad_norm": 2.1363627910614014, "learning_rate": 3.06930693069307e-05, "loss": 0.3731, "step": 1196 }, { "epoch": 2.085440278988666, "grad_norm": 1.2083306312561035, "learning_rate": 3.0634828188701224e-05, "loss": 0.4411, "step": 1197 }, { "epoch": 2.0871839581517, "grad_norm": 1.2809253931045532, "learning_rate": 3.057658707047176e-05, "loss": 0.411, "step": 1198 }, { "epoch": 2.0889276373147343, "grad_norm": 1.0343310832977295, "learning_rate": 3.0518345952242285e-05, "loss": 0.382, "step": 1199 }, { "epoch": 2.090671316477768, "grad_norm": 1.2396420240402222, "learning_rate": 3.0460104834012815e-05, "loss": 0.3493, "step": 1200 }, { "epoch": 2.092414995640802, "grad_norm": 1.3488057851791382, "learning_rate": 3.0401863715783345e-05, "loss": 0.4185, "step": 1201 }, { "epoch": 2.094158674803836, "grad_norm": 1.004125952720642, "learning_rate": 3.0343622597553872e-05, "loss": 0.3656, "step": 1202 }, { "epoch": 2.09590235396687, "grad_norm": 1.545487642288208, "learning_rate": 3.0285381479324403e-05, "loss": 0.4493, "step": 1203 }, { "epoch": 2.0976460331299043, "grad_norm": 0.9234521389007568, "learning_rate": 3.0227140361094936e-05, "loss": 0.3431, "step": 1204 }, { "epoch": 2.099389712292938, "grad_norm": 1.051703691482544, "learning_rate": 3.0168899242865467e-05, "loss": 0.3138, "step": 1205 }, { "epoch": 2.101133391455972, "grad_norm": 1.0501397848129272, "learning_rate": 3.0110658124635994e-05, "loss": 0.4128, "step": 1206 }, { "epoch": 2.102877070619006, "grad_norm": 1.3269686698913574, "learning_rate": 3.0052417006406524e-05, "loss": 0.4588, "step": 1207 }, { "epoch": 2.10462074978204, "grad_norm": 1.2858893871307373, "learning_rate": 2.9994175888177058e-05, "loss": 0.3454, "step": 1208 }, { "epoch": 2.1063644289450743, "grad_norm": 1.3641340732574463, "learning_rate": 2.993593476994758e-05, "loss": 0.4924, "step": 1209 }, { "epoch": 2.108108108108108, "grad_norm": 0.8644853234291077, "learning_rate": 2.9877693651718115e-05, "loss": 0.3296, "step": 1210 }, { "epoch": 2.109851787271142, "grad_norm": 0.9400335550308228, "learning_rate": 2.9819452533488645e-05, "loss": 0.3389, "step": 1211 }, { "epoch": 2.111595466434176, "grad_norm": 0.960182249546051, "learning_rate": 2.9761211415259175e-05, "loss": 0.3436, "step": 1212 }, { "epoch": 2.11333914559721, "grad_norm": 1.2387609481811523, "learning_rate": 2.9702970297029702e-05, "loss": 0.3627, "step": 1213 }, { "epoch": 2.1150828247602442, "grad_norm": 1.1826505661010742, "learning_rate": 2.9644729178800236e-05, "loss": 0.3764, "step": 1214 }, { "epoch": 2.1168265039232783, "grad_norm": 1.0203895568847656, "learning_rate": 2.9586488060570766e-05, "loss": 0.3263, "step": 1215 }, { "epoch": 2.118570183086312, "grad_norm": 0.9682149887084961, "learning_rate": 2.9528246942341293e-05, "loss": 0.3161, "step": 1216 }, { "epoch": 2.120313862249346, "grad_norm": 1.4270073175430298, "learning_rate": 2.9470005824111823e-05, "loss": 0.4095, "step": 1217 }, { "epoch": 2.12205754141238, "grad_norm": 1.2872319221496582, "learning_rate": 2.9411764705882354e-05, "loss": 0.3584, "step": 1218 }, { "epoch": 2.123801220575414, "grad_norm": 1.2522636651992798, "learning_rate": 2.9353523587652887e-05, "loss": 0.428, "step": 1219 }, { "epoch": 2.1255448997384483, "grad_norm": 1.1584253311157227, "learning_rate": 2.9295282469423414e-05, "loss": 0.3651, "step": 1220 }, { "epoch": 2.127288578901482, "grad_norm": 1.431574821472168, "learning_rate": 2.9237041351193945e-05, "loss": 0.4275, "step": 1221 }, { "epoch": 2.129032258064516, "grad_norm": 1.1091755628585815, "learning_rate": 2.9178800232964475e-05, "loss": 0.3156, "step": 1222 }, { "epoch": 2.13077593722755, "grad_norm": 1.26177179813385, "learning_rate": 2.9120559114735002e-05, "loss": 0.4193, "step": 1223 }, { "epoch": 2.132519616390584, "grad_norm": 1.4524120092391968, "learning_rate": 2.9062317996505532e-05, "loss": 0.4029, "step": 1224 }, { "epoch": 2.1342632955536183, "grad_norm": 1.2142481803894043, "learning_rate": 2.9004076878276066e-05, "loss": 0.354, "step": 1225 }, { "epoch": 2.1360069747166524, "grad_norm": 1.2172460556030273, "learning_rate": 2.8945835760046596e-05, "loss": 0.4097, "step": 1226 }, { "epoch": 2.137750653879686, "grad_norm": 0.9824637770652771, "learning_rate": 2.8887594641817123e-05, "loss": 0.324, "step": 1227 }, { "epoch": 2.13949433304272, "grad_norm": 0.96661376953125, "learning_rate": 2.8829353523587653e-05, "loss": 0.2979, "step": 1228 }, { "epoch": 2.141238012205754, "grad_norm": 1.5533130168914795, "learning_rate": 2.8771112405358187e-05, "loss": 0.4322, "step": 1229 }, { "epoch": 2.1429816913687882, "grad_norm": 1.2926884889602661, "learning_rate": 2.871287128712871e-05, "loss": 0.3893, "step": 1230 }, { "epoch": 2.1447253705318223, "grad_norm": 1.2673490047454834, "learning_rate": 2.8654630168899244e-05, "loss": 0.3773, "step": 1231 }, { "epoch": 2.146469049694856, "grad_norm": 1.1456133127212524, "learning_rate": 2.8596389050669775e-05, "loss": 0.3386, "step": 1232 }, { "epoch": 2.14821272885789, "grad_norm": 1.0608532428741455, "learning_rate": 2.8538147932440308e-05, "loss": 0.3559, "step": 1233 }, { "epoch": 2.149956408020924, "grad_norm": 0.9807785153388977, "learning_rate": 2.8479906814210832e-05, "loss": 0.3369, "step": 1234 }, { "epoch": 2.151700087183958, "grad_norm": 1.1711368560791016, "learning_rate": 2.8421665695981365e-05, "loss": 0.412, "step": 1235 }, { "epoch": 2.1534437663469923, "grad_norm": 1.032591462135315, "learning_rate": 2.8363424577751896e-05, "loss": 0.3626, "step": 1236 }, { "epoch": 2.155187445510026, "grad_norm": 1.4786378145217896, "learning_rate": 2.8305183459522423e-05, "loss": 0.4018, "step": 1237 }, { "epoch": 2.15693112467306, "grad_norm": 1.0540741682052612, "learning_rate": 2.8246942341292953e-05, "loss": 0.3731, "step": 1238 }, { "epoch": 2.158674803836094, "grad_norm": 1.0685230493545532, "learning_rate": 2.8188701223063487e-05, "loss": 0.3625, "step": 1239 }, { "epoch": 2.160418482999128, "grad_norm": 1.2617127895355225, "learning_rate": 2.8130460104834017e-05, "loss": 0.3891, "step": 1240 }, { "epoch": 2.1621621621621623, "grad_norm": 1.3102099895477295, "learning_rate": 2.8072218986604544e-05, "loss": 0.3103, "step": 1241 }, { "epoch": 2.1639058413251964, "grad_norm": 1.1483746767044067, "learning_rate": 2.8013977868375074e-05, "loss": 0.4129, "step": 1242 }, { "epoch": 2.16564952048823, "grad_norm": 1.4425313472747803, "learning_rate": 2.7955736750145605e-05, "loss": 0.4328, "step": 1243 }, { "epoch": 2.167393199651264, "grad_norm": 1.4541949033737183, "learning_rate": 2.789749563191613e-05, "loss": 0.3615, "step": 1244 }, { "epoch": 2.169136878814298, "grad_norm": 1.2208092212677002, "learning_rate": 2.7839254513686662e-05, "loss": 0.363, "step": 1245 }, { "epoch": 2.1708805579773323, "grad_norm": 1.2074350118637085, "learning_rate": 2.7781013395457195e-05, "loss": 0.3104, "step": 1246 }, { "epoch": 2.1726242371403663, "grad_norm": 1.2241541147232056, "learning_rate": 2.7722772277227726e-05, "loss": 0.3734, "step": 1247 }, { "epoch": 2.1743679163034, "grad_norm": 1.0574438571929932, "learning_rate": 2.7664531158998253e-05, "loss": 0.3548, "step": 1248 }, { "epoch": 2.176111595466434, "grad_norm": 0.9267942309379578, "learning_rate": 2.7606290040768783e-05, "loss": 0.3403, "step": 1249 }, { "epoch": 2.177855274629468, "grad_norm": 1.174359917640686, "learning_rate": 2.7548048922539317e-05, "loss": 0.3482, "step": 1250 }, { "epoch": 2.1795989537925022, "grad_norm": 1.2943775653839111, "learning_rate": 2.748980780430984e-05, "loss": 0.4052, "step": 1251 }, { "epoch": 2.1813426329555363, "grad_norm": 1.3358867168426514, "learning_rate": 2.7431566686080374e-05, "loss": 0.423, "step": 1252 }, { "epoch": 2.1830863121185704, "grad_norm": 1.2811042070388794, "learning_rate": 2.7373325567850904e-05, "loss": 0.3838, "step": 1253 }, { "epoch": 2.184829991281604, "grad_norm": 1.6066226959228516, "learning_rate": 2.7315084449621438e-05, "loss": 0.4348, "step": 1254 }, { "epoch": 2.186573670444638, "grad_norm": 1.1124838590621948, "learning_rate": 2.725684333139196e-05, "loss": 0.448, "step": 1255 }, { "epoch": 2.188317349607672, "grad_norm": 1.0546717643737793, "learning_rate": 2.7198602213162495e-05, "loss": 0.3408, "step": 1256 }, { "epoch": 2.1900610287707063, "grad_norm": 0.9909789562225342, "learning_rate": 2.7140361094933025e-05, "loss": 0.3619, "step": 1257 }, { "epoch": 2.1918047079337404, "grad_norm": 1.3226134777069092, "learning_rate": 2.7082119976703552e-05, "loss": 0.4253, "step": 1258 }, { "epoch": 2.193548387096774, "grad_norm": 1.13717782497406, "learning_rate": 2.7023878858474083e-05, "loss": 0.4126, "step": 1259 }, { "epoch": 2.195292066259808, "grad_norm": 1.2135651111602783, "learning_rate": 2.6965637740244616e-05, "loss": 0.3608, "step": 1260 }, { "epoch": 2.197035745422842, "grad_norm": 1.3768850564956665, "learning_rate": 2.6907396622015147e-05, "loss": 0.3781, "step": 1261 }, { "epoch": 2.1987794245858763, "grad_norm": 1.2841908931732178, "learning_rate": 2.6849155503785673e-05, "loss": 0.3644, "step": 1262 }, { "epoch": 2.2005231037489104, "grad_norm": 0.9574114680290222, "learning_rate": 2.6790914385556204e-05, "loss": 0.3887, "step": 1263 }, { "epoch": 2.202266782911944, "grad_norm": 0.9209376573562622, "learning_rate": 2.6732673267326734e-05, "loss": 0.3614, "step": 1264 }, { "epoch": 2.204010462074978, "grad_norm": 1.0001102685928345, "learning_rate": 2.667443214909726e-05, "loss": 0.3879, "step": 1265 }, { "epoch": 2.205754141238012, "grad_norm": 0.9837644100189209, "learning_rate": 2.6616191030867795e-05, "loss": 0.3699, "step": 1266 }, { "epoch": 2.2074978204010463, "grad_norm": 0.9509032964706421, "learning_rate": 2.6557949912638325e-05, "loss": 0.3457, "step": 1267 }, { "epoch": 2.2092414995640803, "grad_norm": 1.4652684926986694, "learning_rate": 2.6499708794408855e-05, "loss": 0.378, "step": 1268 }, { "epoch": 2.210985178727114, "grad_norm": 1.1892563104629517, "learning_rate": 2.6441467676179382e-05, "loss": 0.3562, "step": 1269 }, { "epoch": 2.212728857890148, "grad_norm": 1.2659000158309937, "learning_rate": 2.6383226557949912e-05, "loss": 0.3115, "step": 1270 }, { "epoch": 2.214472537053182, "grad_norm": 1.0766676664352417, "learning_rate": 2.6324985439720446e-05, "loss": 0.3722, "step": 1271 }, { "epoch": 2.2162162162162162, "grad_norm": 1.3806028366088867, "learning_rate": 2.6266744321490973e-05, "loss": 0.4063, "step": 1272 }, { "epoch": 2.2179598953792503, "grad_norm": 1.1344889402389526, "learning_rate": 2.6208503203261503e-05, "loss": 0.3436, "step": 1273 }, { "epoch": 2.2197035745422844, "grad_norm": 1.130995273590088, "learning_rate": 2.6150262085032034e-05, "loss": 0.3573, "step": 1274 }, { "epoch": 2.221447253705318, "grad_norm": 1.0826984643936157, "learning_rate": 2.6092020966802567e-05, "loss": 0.3909, "step": 1275 }, { "epoch": 2.223190932868352, "grad_norm": 1.06009840965271, "learning_rate": 2.603377984857309e-05, "loss": 0.3809, "step": 1276 }, { "epoch": 2.224934612031386, "grad_norm": 1.2623368501663208, "learning_rate": 2.5975538730343625e-05, "loss": 0.3941, "step": 1277 }, { "epoch": 2.2266782911944203, "grad_norm": 1.2415335178375244, "learning_rate": 2.5917297612114155e-05, "loss": 0.35, "step": 1278 }, { "epoch": 2.2284219703574544, "grad_norm": 0.9901197552680969, "learning_rate": 2.5859056493884682e-05, "loss": 0.3311, "step": 1279 }, { "epoch": 2.2301656495204885, "grad_norm": 0.9661601781845093, "learning_rate": 2.5800815375655212e-05, "loss": 0.2885, "step": 1280 }, { "epoch": 2.231909328683522, "grad_norm": 1.1147770881652832, "learning_rate": 2.5742574257425746e-05, "loss": 0.3452, "step": 1281 }, { "epoch": 2.233653007846556, "grad_norm": 0.9220090508460999, "learning_rate": 2.5684333139196276e-05, "loss": 0.3238, "step": 1282 }, { "epoch": 2.2353966870095903, "grad_norm": 1.1061185598373413, "learning_rate": 2.5626092020966803e-05, "loss": 0.3662, "step": 1283 }, { "epoch": 2.2371403661726244, "grad_norm": 1.0169193744659424, "learning_rate": 2.5567850902737333e-05, "loss": 0.3573, "step": 1284 }, { "epoch": 2.2388840453356584, "grad_norm": 1.1706228256225586, "learning_rate": 2.5509609784507864e-05, "loss": 0.3761, "step": 1285 }, { "epoch": 2.240627724498692, "grad_norm": 1.012108564376831, "learning_rate": 2.545136866627839e-05, "loss": 0.3208, "step": 1286 }, { "epoch": 2.242371403661726, "grad_norm": 0.9825400114059448, "learning_rate": 2.5393127548048924e-05, "loss": 0.2596, "step": 1287 }, { "epoch": 2.2441150828247602, "grad_norm": 1.5034188032150269, "learning_rate": 2.5334886429819455e-05, "loss": 0.4713, "step": 1288 }, { "epoch": 2.2458587619877943, "grad_norm": 1.0986589193344116, "learning_rate": 2.5276645311589985e-05, "loss": 0.3933, "step": 1289 }, { "epoch": 2.2476024411508284, "grad_norm": 1.170927882194519, "learning_rate": 2.5218404193360512e-05, "loss": 0.3809, "step": 1290 }, { "epoch": 2.249346120313862, "grad_norm": 1.096548318862915, "learning_rate": 2.5160163075131042e-05, "loss": 0.3816, "step": 1291 }, { "epoch": 2.251089799476896, "grad_norm": 1.2232129573822021, "learning_rate": 2.5101921956901576e-05, "loss": 0.3465, "step": 1292 }, { "epoch": 2.25283347863993, "grad_norm": 1.415945291519165, "learning_rate": 2.5043680838672103e-05, "loss": 0.4649, "step": 1293 }, { "epoch": 2.2545771578029643, "grad_norm": 1.2740546464920044, "learning_rate": 2.4985439720442633e-05, "loss": 0.3998, "step": 1294 }, { "epoch": 2.2563208369659984, "grad_norm": 1.058977484703064, "learning_rate": 2.4927198602213163e-05, "loss": 0.3099, "step": 1295 }, { "epoch": 2.258064516129032, "grad_norm": 1.0642662048339844, "learning_rate": 2.4868957483983694e-05, "loss": 0.3638, "step": 1296 }, { "epoch": 2.259808195292066, "grad_norm": 1.1435662508010864, "learning_rate": 2.4810716365754224e-05, "loss": 0.3507, "step": 1297 }, { "epoch": 2.2615518744551, "grad_norm": 1.1366382837295532, "learning_rate": 2.4752475247524754e-05, "loss": 0.3835, "step": 1298 }, { "epoch": 2.2632955536181343, "grad_norm": 1.1118016242980957, "learning_rate": 2.4694234129295284e-05, "loss": 0.3401, "step": 1299 }, { "epoch": 2.2650392327811684, "grad_norm": 0.9317185878753662, "learning_rate": 2.4635993011065815e-05, "loss": 0.2964, "step": 1300 }, { "epoch": 2.2667829119442024, "grad_norm": 1.5480329990386963, "learning_rate": 2.457775189283634e-05, "loss": 0.4256, "step": 1301 }, { "epoch": 2.268526591107236, "grad_norm": 1.3246828317642212, "learning_rate": 2.4519510774606875e-05, "loss": 0.4133, "step": 1302 }, { "epoch": 2.27027027027027, "grad_norm": 1.4295002222061157, "learning_rate": 2.4461269656377402e-05, "loss": 0.4439, "step": 1303 }, { "epoch": 2.2720139494333043, "grad_norm": 1.251286506652832, "learning_rate": 2.4403028538147936e-05, "loss": 0.3603, "step": 1304 }, { "epoch": 2.2737576285963383, "grad_norm": 1.1312212944030762, "learning_rate": 2.4344787419918463e-05, "loss": 0.3608, "step": 1305 }, { "epoch": 2.2755013077593724, "grad_norm": 0.9326503276824951, "learning_rate": 2.4286546301688997e-05, "loss": 0.2965, "step": 1306 }, { "epoch": 2.2772449869224065, "grad_norm": 1.256291151046753, "learning_rate": 2.4228305183459523e-05, "loss": 0.3738, "step": 1307 }, { "epoch": 2.27898866608544, "grad_norm": 0.927047848701477, "learning_rate": 2.4170064065230054e-05, "loss": 0.3096, "step": 1308 }, { "epoch": 2.2807323452484742, "grad_norm": 1.270626187324524, "learning_rate": 2.4111822947000584e-05, "loss": 0.3668, "step": 1309 }, { "epoch": 2.2824760244115083, "grad_norm": 1.019820213317871, "learning_rate": 2.4053581828771114e-05, "loss": 0.3311, "step": 1310 }, { "epoch": 2.2842197035745424, "grad_norm": 1.07931649684906, "learning_rate": 2.3995340710541645e-05, "loss": 0.3297, "step": 1311 }, { "epoch": 2.2859633827375765, "grad_norm": 1.0121482610702515, "learning_rate": 2.393709959231217e-05, "loss": 0.3224, "step": 1312 }, { "epoch": 2.28770706190061, "grad_norm": 1.015043020248413, "learning_rate": 2.3878858474082705e-05, "loss": 0.3255, "step": 1313 }, { "epoch": 2.289450741063644, "grad_norm": 1.0972106456756592, "learning_rate": 2.3820617355853232e-05, "loss": 0.3651, "step": 1314 }, { "epoch": 2.2911944202266783, "grad_norm": 1.1767762899398804, "learning_rate": 2.3762376237623762e-05, "loss": 0.3551, "step": 1315 }, { "epoch": 2.2929380993897124, "grad_norm": 1.3547711372375488, "learning_rate": 2.3704135119394293e-05, "loss": 0.3551, "step": 1316 }, { "epoch": 2.2946817785527465, "grad_norm": 1.0283704996109009, "learning_rate": 2.3645894001164823e-05, "loss": 0.3197, "step": 1317 }, { "epoch": 2.29642545771578, "grad_norm": 1.0089467763900757, "learning_rate": 2.3587652882935353e-05, "loss": 0.3271, "step": 1318 }, { "epoch": 2.298169136878814, "grad_norm": 1.0561933517456055, "learning_rate": 2.3529411764705884e-05, "loss": 0.3964, "step": 1319 }, { "epoch": 2.2999128160418483, "grad_norm": 1.0436279773712158, "learning_rate": 2.3471170646476414e-05, "loss": 0.3562, "step": 1320 }, { "epoch": 2.3016564952048824, "grad_norm": 2.006716728210449, "learning_rate": 2.3412929528246944e-05, "loss": 0.5126, "step": 1321 }, { "epoch": 2.3034001743679164, "grad_norm": 1.213318109512329, "learning_rate": 2.335468841001747e-05, "loss": 0.3821, "step": 1322 }, { "epoch": 2.30514385353095, "grad_norm": 1.041857123374939, "learning_rate": 2.3296447291788005e-05, "loss": 0.3539, "step": 1323 }, { "epoch": 2.306887532693984, "grad_norm": 1.665516972541809, "learning_rate": 2.3238206173558532e-05, "loss": 0.4747, "step": 1324 }, { "epoch": 2.3086312118570183, "grad_norm": 0.9252235889434814, "learning_rate": 2.3179965055329065e-05, "loss": 0.2918, "step": 1325 }, { "epoch": 2.3103748910200523, "grad_norm": 1.0550988912582397, "learning_rate": 2.3121723937099592e-05, "loss": 0.3627, "step": 1326 }, { "epoch": 2.3121185701830864, "grad_norm": 1.5562800168991089, "learning_rate": 2.3063482818870126e-05, "loss": 0.3863, "step": 1327 }, { "epoch": 2.3138622493461205, "grad_norm": 1.27681303024292, "learning_rate": 2.3005241700640653e-05, "loss": 0.3151, "step": 1328 }, { "epoch": 2.315605928509154, "grad_norm": 1.3210787773132324, "learning_rate": 2.2947000582411183e-05, "loss": 0.3973, "step": 1329 }, { "epoch": 2.3173496076721882, "grad_norm": 1.4356781244277954, "learning_rate": 2.2888759464181714e-05, "loss": 0.4333, "step": 1330 }, { "epoch": 2.3190932868352223, "grad_norm": 1.437955379486084, "learning_rate": 2.2830518345952244e-05, "loss": 0.4495, "step": 1331 }, { "epoch": 2.3208369659982564, "grad_norm": 1.302354097366333, "learning_rate": 2.2772277227722774e-05, "loss": 0.4163, "step": 1332 }, { "epoch": 2.3225806451612905, "grad_norm": 1.3720670938491821, "learning_rate": 2.2714036109493305e-05, "loss": 0.4132, "step": 1333 }, { "epoch": 2.3243243243243246, "grad_norm": 1.1474231481552124, "learning_rate": 2.2655794991263835e-05, "loss": 0.3901, "step": 1334 }, { "epoch": 2.326068003487358, "grad_norm": 1.3044073581695557, "learning_rate": 2.2597553873034362e-05, "loss": 0.3805, "step": 1335 }, { "epoch": 2.3278116826503923, "grad_norm": 1.3397935628890991, "learning_rate": 2.2539312754804892e-05, "loss": 0.4164, "step": 1336 }, { "epoch": 2.3295553618134264, "grad_norm": 1.0424234867095947, "learning_rate": 2.2481071636575422e-05, "loss": 0.365, "step": 1337 }, { "epoch": 2.3312990409764605, "grad_norm": 1.2012394666671753, "learning_rate": 2.2422830518345953e-05, "loss": 0.3772, "step": 1338 }, { "epoch": 2.3330427201394945, "grad_norm": 1.0020631551742554, "learning_rate": 2.2364589400116483e-05, "loss": 0.3393, "step": 1339 }, { "epoch": 2.334786399302528, "grad_norm": 0.8543850183486938, "learning_rate": 2.2306348281887013e-05, "loss": 0.3023, "step": 1340 }, { "epoch": 2.3365300784655623, "grad_norm": 1.6075738668441772, "learning_rate": 2.2248107163657544e-05, "loss": 0.4746, "step": 1341 }, { "epoch": 2.3382737576285963, "grad_norm": 0.9920380115509033, "learning_rate": 2.2189866045428074e-05, "loss": 0.3757, "step": 1342 }, { "epoch": 2.3400174367916304, "grad_norm": 1.0415147542953491, "learning_rate": 2.21316249271986e-05, "loss": 0.3263, "step": 1343 }, { "epoch": 2.3417611159546645, "grad_norm": 1.159276008605957, "learning_rate": 2.2073383808969134e-05, "loss": 0.3852, "step": 1344 }, { "epoch": 2.343504795117698, "grad_norm": 1.2699120044708252, "learning_rate": 2.201514269073966e-05, "loss": 0.4396, "step": 1345 }, { "epoch": 2.3452484742807322, "grad_norm": 0.9606801271438599, "learning_rate": 2.1956901572510195e-05, "loss": 0.3341, "step": 1346 }, { "epoch": 2.3469921534437663, "grad_norm": 1.2029986381530762, "learning_rate": 2.1898660454280722e-05, "loss": 0.3478, "step": 1347 }, { "epoch": 2.3487358326068004, "grad_norm": 1.7829408645629883, "learning_rate": 2.1840419336051256e-05, "loss": 0.4736, "step": 1348 }, { "epoch": 2.3504795117698345, "grad_norm": 1.240458607673645, "learning_rate": 2.1782178217821783e-05, "loss": 0.3777, "step": 1349 }, { "epoch": 2.352223190932868, "grad_norm": 1.360583782196045, "learning_rate": 2.1723937099592313e-05, "loss": 0.3896, "step": 1350 }, { "epoch": 2.353966870095902, "grad_norm": 1.1344939470291138, "learning_rate": 2.1665695981362843e-05, "loss": 0.3555, "step": 1351 }, { "epoch": 2.3557105492589363, "grad_norm": 1.3654825687408447, "learning_rate": 2.1607454863133373e-05, "loss": 0.3977, "step": 1352 }, { "epoch": 2.3574542284219704, "grad_norm": 1.3979376554489136, "learning_rate": 2.1549213744903904e-05, "loss": 0.4069, "step": 1353 }, { "epoch": 2.3591979075850045, "grad_norm": 1.2004948854446411, "learning_rate": 2.1490972626674434e-05, "loss": 0.3721, "step": 1354 }, { "epoch": 2.360941586748038, "grad_norm": 1.0786032676696777, "learning_rate": 2.1432731508444964e-05, "loss": 0.3588, "step": 1355 }, { "epoch": 2.362685265911072, "grad_norm": 0.8125416040420532, "learning_rate": 2.1374490390215495e-05, "loss": 0.2957, "step": 1356 }, { "epoch": 2.3644289450741063, "grad_norm": 0.9739161133766174, "learning_rate": 2.131624927198602e-05, "loss": 0.347, "step": 1357 }, { "epoch": 2.3661726242371404, "grad_norm": 1.0482184886932373, "learning_rate": 2.1258008153756552e-05, "loss": 0.3617, "step": 1358 }, { "epoch": 2.3679163034001744, "grad_norm": 1.107926845550537, "learning_rate": 2.1199767035527082e-05, "loss": 0.379, "step": 1359 }, { "epoch": 2.3696599825632085, "grad_norm": 1.7347232103347778, "learning_rate": 2.1141525917297612e-05, "loss": 0.4288, "step": 1360 }, { "epoch": 2.3714036617262426, "grad_norm": 1.0190845727920532, "learning_rate": 2.1083284799068143e-05, "loss": 0.3074, "step": 1361 }, { "epoch": 2.3731473408892763, "grad_norm": 1.3375804424285889, "learning_rate": 2.1025043680838673e-05, "loss": 0.3622, "step": 1362 }, { "epoch": 2.3748910200523103, "grad_norm": 0.9622097015380859, "learning_rate": 2.0966802562609203e-05, "loss": 0.2891, "step": 1363 }, { "epoch": 2.3766346992153444, "grad_norm": 0.9909211993217468, "learning_rate": 2.090856144437973e-05, "loss": 0.326, "step": 1364 }, { "epoch": 2.3783783783783785, "grad_norm": 1.0160837173461914, "learning_rate": 2.0850320326150264e-05, "loss": 0.3318, "step": 1365 }, { "epoch": 2.3801220575414126, "grad_norm": 1.1147747039794922, "learning_rate": 2.079207920792079e-05, "loss": 0.3385, "step": 1366 }, { "epoch": 2.3818657367044462, "grad_norm": 1.6563867330551147, "learning_rate": 2.0733838089691325e-05, "loss": 0.3854, "step": 1367 }, { "epoch": 2.3836094158674803, "grad_norm": 1.3365051746368408, "learning_rate": 2.067559697146185e-05, "loss": 0.426, "step": 1368 }, { "epoch": 2.3853530950305144, "grad_norm": 1.7695646286010742, "learning_rate": 2.0617355853232385e-05, "loss": 0.4601, "step": 1369 }, { "epoch": 2.3870967741935485, "grad_norm": 1.0509486198425293, "learning_rate": 2.0559114735002912e-05, "loss": 0.3533, "step": 1370 }, { "epoch": 2.3888404533565826, "grad_norm": 1.1707298755645752, "learning_rate": 2.0500873616773442e-05, "loss": 0.3413, "step": 1371 }, { "epoch": 2.390584132519616, "grad_norm": 1.1510952711105347, "learning_rate": 2.0442632498543973e-05, "loss": 0.3768, "step": 1372 }, { "epoch": 2.3923278116826503, "grad_norm": 1.8856801986694336, "learning_rate": 2.0384391380314503e-05, "loss": 0.4942, "step": 1373 }, { "epoch": 2.3940714908456844, "grad_norm": 1.1923797130584717, "learning_rate": 2.0326150262085033e-05, "loss": 0.364, "step": 1374 }, { "epoch": 2.3958151700087185, "grad_norm": 1.5718883275985718, "learning_rate": 2.0267909143855564e-05, "loss": 0.4392, "step": 1375 }, { "epoch": 2.3975588491717525, "grad_norm": 1.1370424032211304, "learning_rate": 2.0209668025626094e-05, "loss": 0.3937, "step": 1376 }, { "epoch": 2.399302528334786, "grad_norm": 1.0262521505355835, "learning_rate": 2.0151426907396624e-05, "loss": 0.3262, "step": 1377 }, { "epoch": 2.4010462074978203, "grad_norm": 1.1972631216049194, "learning_rate": 2.0093185789167155e-05, "loss": 0.3102, "step": 1378 }, { "epoch": 2.4027898866608544, "grad_norm": 2.8938565254211426, "learning_rate": 2.0034944670937685e-05, "loss": 0.428, "step": 1379 }, { "epoch": 2.4045335658238884, "grad_norm": 1.3735921382904053, "learning_rate": 1.9976703552708212e-05, "loss": 0.4003, "step": 1380 }, { "epoch": 2.4062772449869225, "grad_norm": 1.3124562501907349, "learning_rate": 1.9918462434478742e-05, "loss": 0.3827, "step": 1381 }, { "epoch": 2.408020924149956, "grad_norm": 1.1652342081069946, "learning_rate": 1.9860221316249272e-05, "loss": 0.3944, "step": 1382 }, { "epoch": 2.4097646033129902, "grad_norm": 1.1393159627914429, "learning_rate": 1.9801980198019803e-05, "loss": 0.4089, "step": 1383 }, { "epoch": 2.4115082824760243, "grad_norm": 1.0534279346466064, "learning_rate": 1.9743739079790333e-05, "loss": 0.3527, "step": 1384 }, { "epoch": 2.4132519616390584, "grad_norm": 1.3852057456970215, "learning_rate": 1.9685497961560863e-05, "loss": 0.4218, "step": 1385 }, { "epoch": 2.4149956408020925, "grad_norm": 0.9963579177856445, "learning_rate": 1.9627256843331394e-05, "loss": 0.2789, "step": 1386 }, { "epoch": 2.4167393199651266, "grad_norm": 1.00745689868927, "learning_rate": 1.956901572510192e-05, "loss": 0.2854, "step": 1387 }, { "epoch": 2.4184829991281602, "grad_norm": 1.0842740535736084, "learning_rate": 1.9510774606872454e-05, "loss": 0.3704, "step": 1388 }, { "epoch": 2.4202266782911943, "grad_norm": 0.9825806617736816, "learning_rate": 1.945253348864298e-05, "loss": 0.2877, "step": 1389 }, { "epoch": 2.4219703574542284, "grad_norm": 1.039016604423523, "learning_rate": 1.9394292370413515e-05, "loss": 0.3346, "step": 1390 }, { "epoch": 2.4237140366172625, "grad_norm": 1.3312251567840576, "learning_rate": 1.933605125218404e-05, "loss": 0.4069, "step": 1391 }, { "epoch": 2.4254577157802966, "grad_norm": 1.0655421018600464, "learning_rate": 1.9277810133954575e-05, "loss": 0.3037, "step": 1392 }, { "epoch": 2.4272013949433306, "grad_norm": 1.060248613357544, "learning_rate": 1.9219569015725102e-05, "loss": 0.3477, "step": 1393 }, { "epoch": 2.4289450741063643, "grad_norm": 1.0524959564208984, "learning_rate": 1.9161327897495633e-05, "loss": 0.2963, "step": 1394 }, { "epoch": 2.4306887532693984, "grad_norm": 1.1642735004425049, "learning_rate": 1.9103086779266163e-05, "loss": 0.3314, "step": 1395 }, { "epoch": 2.4324324324324325, "grad_norm": 1.424885869026184, "learning_rate": 1.9044845661036693e-05, "loss": 0.3901, "step": 1396 }, { "epoch": 2.4341761115954665, "grad_norm": 1.1209498643875122, "learning_rate": 1.8986604542807223e-05, "loss": 0.3877, "step": 1397 }, { "epoch": 2.4359197907585006, "grad_norm": 1.4270612001419067, "learning_rate": 1.8928363424577754e-05, "loss": 0.4112, "step": 1398 }, { "epoch": 2.4376634699215343, "grad_norm": 1.1720356941223145, "learning_rate": 1.8870122306348284e-05, "loss": 0.365, "step": 1399 }, { "epoch": 2.4394071490845683, "grad_norm": 1.1501771211624146, "learning_rate": 1.8811881188118814e-05, "loss": 0.3691, "step": 1400 }, { "epoch": 2.4411508282476024, "grad_norm": 1.1231385469436646, "learning_rate": 1.875364006988934e-05, "loss": 0.3495, "step": 1401 }, { "epoch": 2.4428945074106365, "grad_norm": 1.1934847831726074, "learning_rate": 1.869539895165987e-05, "loss": 0.3766, "step": 1402 }, { "epoch": 2.4446381865736706, "grad_norm": 0.8858659863471985, "learning_rate": 1.8637157833430402e-05, "loss": 0.2911, "step": 1403 }, { "epoch": 2.4463818657367042, "grad_norm": 1.2591729164123535, "learning_rate": 1.8578916715200932e-05, "loss": 0.3189, "step": 1404 }, { "epoch": 2.4481255448997383, "grad_norm": 1.208404302597046, "learning_rate": 1.8520675596971462e-05, "loss": 0.3625, "step": 1405 }, { "epoch": 2.4498692240627724, "grad_norm": 1.1765135526657104, "learning_rate": 1.8462434478741993e-05, "loss": 0.4306, "step": 1406 }, { "epoch": 2.4516129032258065, "grad_norm": 1.1665065288543701, "learning_rate": 1.8404193360512523e-05, "loss": 0.3984, "step": 1407 }, { "epoch": 2.4533565823888406, "grad_norm": 1.3652561902999878, "learning_rate": 1.834595224228305e-05, "loss": 0.4248, "step": 1408 }, { "epoch": 2.455100261551874, "grad_norm": 1.113958477973938, "learning_rate": 1.8287711124053584e-05, "loss": 0.3856, "step": 1409 }, { "epoch": 2.4568439407149083, "grad_norm": 1.4209753274917603, "learning_rate": 1.822947000582411e-05, "loss": 0.3638, "step": 1410 }, { "epoch": 2.4585876198779424, "grad_norm": 0.9565431475639343, "learning_rate": 1.8171228887594644e-05, "loss": 0.3554, "step": 1411 }, { "epoch": 2.4603312990409765, "grad_norm": 1.1251710653305054, "learning_rate": 1.811298776936517e-05, "loss": 0.3096, "step": 1412 }, { "epoch": 2.4620749782040106, "grad_norm": 1.5421477556228638, "learning_rate": 1.8054746651135705e-05, "loss": 0.43, "step": 1413 }, { "epoch": 2.4638186573670446, "grad_norm": 1.5822457075119019, "learning_rate": 1.7996505532906232e-05, "loss": 0.4481, "step": 1414 }, { "epoch": 2.4655623365300783, "grad_norm": 1.0383166074752808, "learning_rate": 1.7938264414676762e-05, "loss": 0.3455, "step": 1415 }, { "epoch": 2.4673060156931124, "grad_norm": 1.3621305227279663, "learning_rate": 1.7880023296447292e-05, "loss": 0.3872, "step": 1416 }, { "epoch": 2.4690496948561464, "grad_norm": 1.2298905849456787, "learning_rate": 1.7821782178217823e-05, "loss": 0.3847, "step": 1417 }, { "epoch": 2.4707933740191805, "grad_norm": 1.283293604850769, "learning_rate": 1.7763541059988353e-05, "loss": 0.2905, "step": 1418 }, { "epoch": 2.4725370531822146, "grad_norm": 1.171015977859497, "learning_rate": 1.7705299941758883e-05, "loss": 0.3805, "step": 1419 }, { "epoch": 2.4742807323452487, "grad_norm": 1.3178833723068237, "learning_rate": 1.7647058823529414e-05, "loss": 0.4245, "step": 1420 }, { "epoch": 2.4760244115082823, "grad_norm": 1.1119165420532227, "learning_rate": 1.7588817705299944e-05, "loss": 0.3438, "step": 1421 }, { "epoch": 2.4777680906713164, "grad_norm": 1.0213501453399658, "learning_rate": 1.753057658707047e-05, "loss": 0.359, "step": 1422 }, { "epoch": 2.4795117698343505, "grad_norm": 1.0041428804397583, "learning_rate": 1.7472335468841005e-05, "loss": 0.3544, "step": 1423 }, { "epoch": 2.4812554489973846, "grad_norm": 2.1581385135650635, "learning_rate": 1.741409435061153e-05, "loss": 0.3684, "step": 1424 }, { "epoch": 2.4829991281604187, "grad_norm": 0.9630132913589478, "learning_rate": 1.7355853232382062e-05, "loss": 0.3363, "step": 1425 }, { "epoch": 2.4847428073234523, "grad_norm": 1.108979344367981, "learning_rate": 1.7297612114152592e-05, "loss": 0.3513, "step": 1426 }, { "epoch": 2.4864864864864864, "grad_norm": 1.0819721221923828, "learning_rate": 1.7239370995923122e-05, "loss": 0.3938, "step": 1427 }, { "epoch": 2.4882301656495205, "grad_norm": 1.0121541023254395, "learning_rate": 1.7181129877693653e-05, "loss": 0.2697, "step": 1428 }, { "epoch": 2.4899738448125546, "grad_norm": 1.0760289430618286, "learning_rate": 1.7122888759464183e-05, "loss": 0.3411, "step": 1429 }, { "epoch": 2.4917175239755887, "grad_norm": 1.0355807542800903, "learning_rate": 1.7064647641234713e-05, "loss": 0.3342, "step": 1430 }, { "epoch": 2.4934612031386223, "grad_norm": 0.9502600431442261, "learning_rate": 1.700640652300524e-05, "loss": 0.2578, "step": 1431 }, { "epoch": 2.4952048823016564, "grad_norm": 1.4440661668777466, "learning_rate": 1.6948165404775774e-05, "loss": 0.4523, "step": 1432 }, { "epoch": 2.4969485614646905, "grad_norm": 1.7829540967941284, "learning_rate": 1.68899242865463e-05, "loss": 0.4337, "step": 1433 }, { "epoch": 2.4986922406277245, "grad_norm": 1.1635067462921143, "learning_rate": 1.6831683168316834e-05, "loss": 0.3269, "step": 1434 }, { "epoch": 2.5004359197907586, "grad_norm": 1.193181037902832, "learning_rate": 1.677344205008736e-05, "loss": 0.3507, "step": 1435 }, { "epoch": 2.5021795989537923, "grad_norm": 0.9108441472053528, "learning_rate": 1.671520093185789e-05, "loss": 0.2793, "step": 1436 }, { "epoch": 2.5039232781168264, "grad_norm": 1.3578112125396729, "learning_rate": 1.6656959813628422e-05, "loss": 0.3641, "step": 1437 }, { "epoch": 2.5056669572798604, "grad_norm": 1.244971513748169, "learning_rate": 1.6598718695398952e-05, "loss": 0.3526, "step": 1438 }, { "epoch": 2.5074106364428945, "grad_norm": 1.2589071989059448, "learning_rate": 1.6540477577169483e-05, "loss": 0.3642, "step": 1439 }, { "epoch": 2.5091543156059286, "grad_norm": 1.4545053243637085, "learning_rate": 1.6482236458940013e-05, "loss": 0.4281, "step": 1440 }, { "epoch": 2.5108979947689622, "grad_norm": 1.3251041173934937, "learning_rate": 1.6423995340710543e-05, "loss": 0.4004, "step": 1441 }, { "epoch": 2.5126416739319968, "grad_norm": 1.5702704191207886, "learning_rate": 1.6365754222481073e-05, "loss": 0.4452, "step": 1442 }, { "epoch": 2.5143853530950304, "grad_norm": 1.3717435598373413, "learning_rate": 1.63075131042516e-05, "loss": 0.3941, "step": 1443 }, { "epoch": 2.5161290322580645, "grad_norm": 1.266982078552246, "learning_rate": 1.6249271986022134e-05, "loss": 0.3319, "step": 1444 }, { "epoch": 2.5178727114210986, "grad_norm": 1.2833482027053833, "learning_rate": 1.619103086779266e-05, "loss": 0.3902, "step": 1445 }, { "epoch": 2.5196163905841327, "grad_norm": 1.298520565032959, "learning_rate": 1.6132789749563195e-05, "loss": 0.3687, "step": 1446 }, { "epoch": 2.5213600697471668, "grad_norm": 1.4334594011306763, "learning_rate": 1.607454863133372e-05, "loss": 0.4192, "step": 1447 }, { "epoch": 2.5231037489102004, "grad_norm": 1.54487144947052, "learning_rate": 1.6016307513104252e-05, "loss": 0.5221, "step": 1448 }, { "epoch": 2.5248474280732345, "grad_norm": 1.6444878578186035, "learning_rate": 1.5958066394874782e-05, "loss": 0.4497, "step": 1449 }, { "epoch": 2.5265911072362686, "grad_norm": 1.9393885135650635, "learning_rate": 1.5899825276645312e-05, "loss": 0.4516, "step": 1450 }, { "epoch": 2.5283347863993026, "grad_norm": 1.4467649459838867, "learning_rate": 1.5841584158415843e-05, "loss": 0.3433, "step": 1451 }, { "epoch": 2.5300784655623367, "grad_norm": 1.1304216384887695, "learning_rate": 1.578334304018637e-05, "loss": 0.3308, "step": 1452 }, { "epoch": 2.5318221447253704, "grad_norm": 1.1503081321716309, "learning_rate": 1.5725101921956903e-05, "loss": 0.367, "step": 1453 }, { "epoch": 2.5335658238884045, "grad_norm": 1.4209166765213013, "learning_rate": 1.566686080372743e-05, "loss": 0.4087, "step": 1454 }, { "epoch": 2.5353095030514385, "grad_norm": 1.259696125984192, "learning_rate": 1.5608619685497964e-05, "loss": 0.4128, "step": 1455 }, { "epoch": 2.5370531822144726, "grad_norm": 1.453859806060791, "learning_rate": 1.555037856726849e-05, "loss": 0.3978, "step": 1456 }, { "epoch": 2.5387968613775067, "grad_norm": 1.0443884134292603, "learning_rate": 1.5492137449039025e-05, "loss": 0.3272, "step": 1457 }, { "epoch": 2.5405405405405403, "grad_norm": 1.1419354677200317, "learning_rate": 1.543389633080955e-05, "loss": 0.3842, "step": 1458 }, { "epoch": 2.5422842197035744, "grad_norm": 1.0947927236557007, "learning_rate": 1.5375655212580082e-05, "loss": 0.362, "step": 1459 }, { "epoch": 2.5440278988666085, "grad_norm": 0.9845089316368103, "learning_rate": 1.5317414094350612e-05, "loss": 0.3139, "step": 1460 }, { "epoch": 2.5457715780296426, "grad_norm": 1.4806652069091797, "learning_rate": 1.5259172976121142e-05, "loss": 0.4223, "step": 1461 }, { "epoch": 2.5475152571926767, "grad_norm": 1.0505174398422241, "learning_rate": 1.5200931857891673e-05, "loss": 0.3451, "step": 1462 }, { "epoch": 2.5492589363557103, "grad_norm": 1.0329346656799316, "learning_rate": 1.5142690739662201e-05, "loss": 0.3252, "step": 1463 }, { "epoch": 2.5510026155187444, "grad_norm": 1.1046292781829834, "learning_rate": 1.5084449621432733e-05, "loss": 0.2987, "step": 1464 }, { "epoch": 2.5527462946817785, "grad_norm": 0.948883056640625, "learning_rate": 1.5026208503203262e-05, "loss": 0.3154, "step": 1465 }, { "epoch": 2.5544899738448126, "grad_norm": 1.5235931873321533, "learning_rate": 1.496796738497379e-05, "loss": 0.3509, "step": 1466 }, { "epoch": 2.5562336530078467, "grad_norm": 1.170962929725647, "learning_rate": 1.4909726266744323e-05, "loss": 0.3801, "step": 1467 }, { "epoch": 2.5579773321708803, "grad_norm": 1.4457343816757202, "learning_rate": 1.4851485148514851e-05, "loss": 0.4011, "step": 1468 }, { "epoch": 2.559721011333915, "grad_norm": 1.008467435836792, "learning_rate": 1.4793244030285383e-05, "loss": 0.3237, "step": 1469 }, { "epoch": 2.5614646904969485, "grad_norm": 1.1821050643920898, "learning_rate": 1.4735002912055912e-05, "loss": 0.4047, "step": 1470 }, { "epoch": 2.5632083696599826, "grad_norm": 1.5890429019927979, "learning_rate": 1.4676761793826444e-05, "loss": 0.4128, "step": 1471 }, { "epoch": 2.5649520488230166, "grad_norm": 1.0048402547836304, "learning_rate": 1.4618520675596972e-05, "loss": 0.3198, "step": 1472 }, { "epoch": 2.5666957279860507, "grad_norm": 1.0806496143341064, "learning_rate": 1.4560279557367501e-05, "loss": 0.3425, "step": 1473 }, { "epoch": 2.568439407149085, "grad_norm": 1.3728445768356323, "learning_rate": 1.4502038439138033e-05, "loss": 0.3989, "step": 1474 }, { "epoch": 2.5701830863121184, "grad_norm": 1.201524257659912, "learning_rate": 1.4443797320908562e-05, "loss": 0.377, "step": 1475 }, { "epoch": 2.5719267654751525, "grad_norm": 1.1296720504760742, "learning_rate": 1.4385556202679094e-05, "loss": 0.3644, "step": 1476 }, { "epoch": 2.5736704446381866, "grad_norm": 1.1805073022842407, "learning_rate": 1.4327315084449622e-05, "loss": 0.3612, "step": 1477 }, { "epoch": 2.5754141238012207, "grad_norm": 1.841667652130127, "learning_rate": 1.4269073966220154e-05, "loss": 0.383, "step": 1478 }, { "epoch": 2.577157802964255, "grad_norm": 1.0553255081176758, "learning_rate": 1.4210832847990683e-05, "loss": 0.3311, "step": 1479 }, { "epoch": 2.5789014821272884, "grad_norm": 1.1370781660079956, "learning_rate": 1.4152591729761211e-05, "loss": 0.3372, "step": 1480 }, { "epoch": 2.5806451612903225, "grad_norm": 1.1243231296539307, "learning_rate": 1.4094350611531743e-05, "loss": 0.3003, "step": 1481 }, { "epoch": 2.5823888404533566, "grad_norm": 1.1495712995529175, "learning_rate": 1.4036109493302272e-05, "loss": 0.3322, "step": 1482 }, { "epoch": 2.5841325196163907, "grad_norm": 1.55241858959198, "learning_rate": 1.3977868375072802e-05, "loss": 0.4631, "step": 1483 }, { "epoch": 2.5858761987794248, "grad_norm": 1.5438967943191528, "learning_rate": 1.3919627256843331e-05, "loss": 0.4692, "step": 1484 }, { "epoch": 2.5876198779424584, "grad_norm": 1.0704858303070068, "learning_rate": 1.3861386138613863e-05, "loss": 0.3192, "step": 1485 }, { "epoch": 2.5893635571054925, "grad_norm": 0.993470311164856, "learning_rate": 1.3803145020384391e-05, "loss": 0.2684, "step": 1486 }, { "epoch": 2.5911072362685266, "grad_norm": 1.0989640951156616, "learning_rate": 1.374490390215492e-05, "loss": 0.3304, "step": 1487 }, { "epoch": 2.5928509154315607, "grad_norm": 1.7261906862258911, "learning_rate": 1.3686662783925452e-05, "loss": 0.4564, "step": 1488 }, { "epoch": 2.5945945945945947, "grad_norm": 1.134470820426941, "learning_rate": 1.362842166569598e-05, "loss": 0.3838, "step": 1489 }, { "epoch": 2.5963382737576284, "grad_norm": 1.056108832359314, "learning_rate": 1.3570180547466513e-05, "loss": 0.3541, "step": 1490 }, { "epoch": 2.5980819529206625, "grad_norm": 1.3624918460845947, "learning_rate": 1.3511939429237041e-05, "loss": 0.3421, "step": 1491 }, { "epoch": 2.5998256320836965, "grad_norm": 0.9250710606575012, "learning_rate": 1.3453698311007573e-05, "loss": 0.3071, "step": 1492 }, { "epoch": 2.6015693112467306, "grad_norm": 1.3135117292404175, "learning_rate": 1.3395457192778102e-05, "loss": 0.3783, "step": 1493 }, { "epoch": 2.6033129904097647, "grad_norm": 1.033918857574463, "learning_rate": 1.333721607454863e-05, "loss": 0.3287, "step": 1494 }, { "epoch": 2.6050566695727984, "grad_norm": 1.1152126789093018, "learning_rate": 1.3278974956319162e-05, "loss": 0.3771, "step": 1495 }, { "epoch": 2.606800348735833, "grad_norm": 1.1294386386871338, "learning_rate": 1.3220733838089691e-05, "loss": 0.3764, "step": 1496 }, { "epoch": 2.6085440278988665, "grad_norm": 1.152246356010437, "learning_rate": 1.3162492719860223e-05, "loss": 0.3812, "step": 1497 }, { "epoch": 2.6102877070619006, "grad_norm": 1.598734974861145, "learning_rate": 1.3104251601630752e-05, "loss": 0.4447, "step": 1498 }, { "epoch": 2.6120313862249347, "grad_norm": 1.0008230209350586, "learning_rate": 1.3046010483401284e-05, "loss": 0.3214, "step": 1499 }, { "epoch": 2.6137750653879688, "grad_norm": 1.2007118463516235, "learning_rate": 1.2987769365171812e-05, "loss": 0.346, "step": 1500 }, { "epoch": 2.615518744551003, "grad_norm": 1.9922611713409424, "learning_rate": 1.2929528246942341e-05, "loss": 0.5498, "step": 1501 }, { "epoch": 2.6172624237140365, "grad_norm": 1.329325556755066, "learning_rate": 1.2871287128712873e-05, "loss": 0.3836, "step": 1502 }, { "epoch": 2.6190061028770706, "grad_norm": 1.106474757194519, "learning_rate": 1.2813046010483402e-05, "loss": 0.3321, "step": 1503 }, { "epoch": 2.6207497820401047, "grad_norm": 1.1519031524658203, "learning_rate": 1.2754804892253932e-05, "loss": 0.3686, "step": 1504 }, { "epoch": 2.6224934612031388, "grad_norm": 1.4570289850234985, "learning_rate": 1.2696563774024462e-05, "loss": 0.3916, "step": 1505 }, { "epoch": 2.624237140366173, "grad_norm": 1.3838889598846436, "learning_rate": 1.2638322655794992e-05, "loss": 0.418, "step": 1506 }, { "epoch": 2.6259808195292065, "grad_norm": 1.325498104095459, "learning_rate": 1.2580081537565521e-05, "loss": 0.4153, "step": 1507 }, { "epoch": 2.6277244986922406, "grad_norm": 1.1977784633636475, "learning_rate": 1.2521840419336051e-05, "loss": 0.3342, "step": 1508 }, { "epoch": 2.6294681778552746, "grad_norm": 1.0455048084259033, "learning_rate": 1.2463599301106582e-05, "loss": 0.3629, "step": 1509 }, { "epoch": 2.6312118570183087, "grad_norm": 1.190539002418518, "learning_rate": 1.2405358182877112e-05, "loss": 0.3498, "step": 1510 }, { "epoch": 2.632955536181343, "grad_norm": 0.9173940420150757, "learning_rate": 1.2347117064647642e-05, "loss": 0.3383, "step": 1511 }, { "epoch": 2.6346992153443765, "grad_norm": 1.3373960256576538, "learning_rate": 1.228887594641817e-05, "loss": 0.4032, "step": 1512 }, { "epoch": 2.6364428945074105, "grad_norm": 1.121806263923645, "learning_rate": 1.2230634828188701e-05, "loss": 0.3355, "step": 1513 }, { "epoch": 2.6381865736704446, "grad_norm": 1.177630066871643, "learning_rate": 1.2172393709959231e-05, "loss": 0.3467, "step": 1514 }, { "epoch": 2.6399302528334787, "grad_norm": 1.3884475231170654, "learning_rate": 1.2114152591729762e-05, "loss": 0.4002, "step": 1515 }, { "epoch": 2.641673931996513, "grad_norm": 1.3229795694351196, "learning_rate": 1.2055911473500292e-05, "loss": 0.3987, "step": 1516 }, { "epoch": 2.6434176111595464, "grad_norm": 1.548869252204895, "learning_rate": 1.1997670355270822e-05, "loss": 0.414, "step": 1517 }, { "epoch": 2.6451612903225805, "grad_norm": 1.0773584842681885, "learning_rate": 1.1939429237041353e-05, "loss": 0.339, "step": 1518 }, { "epoch": 2.6469049694856146, "grad_norm": 1.095578670501709, "learning_rate": 1.1881188118811881e-05, "loss": 0.3353, "step": 1519 }, { "epoch": 2.6486486486486487, "grad_norm": 4.018739223480225, "learning_rate": 1.1822947000582412e-05, "loss": 0.3616, "step": 1520 }, { "epoch": 2.6503923278116828, "grad_norm": 1.2774028778076172, "learning_rate": 1.1764705882352942e-05, "loss": 0.3728, "step": 1521 }, { "epoch": 2.6521360069747164, "grad_norm": 1.1556378602981567, "learning_rate": 1.1706464764123472e-05, "loss": 0.3238, "step": 1522 }, { "epoch": 2.6538796861377505, "grad_norm": 1.1322635412216187, "learning_rate": 1.1648223645894002e-05, "loss": 0.3395, "step": 1523 }, { "epoch": 2.6556233653007846, "grad_norm": 1.3038195371627808, "learning_rate": 1.1589982527664533e-05, "loss": 0.3801, "step": 1524 }, { "epoch": 2.6573670444638187, "grad_norm": 1.1165194511413574, "learning_rate": 1.1531741409435063e-05, "loss": 0.3405, "step": 1525 }, { "epoch": 2.6591107236268527, "grad_norm": 1.3741716146469116, "learning_rate": 1.1473500291205592e-05, "loss": 0.4011, "step": 1526 }, { "epoch": 2.6608544027898864, "grad_norm": 1.4480574131011963, "learning_rate": 1.1415259172976122e-05, "loss": 0.4073, "step": 1527 }, { "epoch": 2.662598081952921, "grad_norm": 1.1404104232788086, "learning_rate": 1.1357018054746652e-05, "loss": 0.3235, "step": 1528 }, { "epoch": 2.6643417611159546, "grad_norm": 1.107757329940796, "learning_rate": 1.1298776936517181e-05, "loss": 0.3488, "step": 1529 }, { "epoch": 2.6660854402789886, "grad_norm": 1.1984657049179077, "learning_rate": 1.1240535818287711e-05, "loss": 0.3761, "step": 1530 }, { "epoch": 2.6678291194420227, "grad_norm": 1.2700718641281128, "learning_rate": 1.1182294700058241e-05, "loss": 0.3514, "step": 1531 }, { "epoch": 2.669572798605057, "grad_norm": 1.1132646799087524, "learning_rate": 1.1124053581828772e-05, "loss": 0.3525, "step": 1532 }, { "epoch": 2.671316477768091, "grad_norm": 1.6162455081939697, "learning_rate": 1.10658124635993e-05, "loss": 0.429, "step": 1533 }, { "epoch": 2.6730601569311245, "grad_norm": 1.23842453956604, "learning_rate": 1.100757134536983e-05, "loss": 0.3632, "step": 1534 }, { "epoch": 2.6748038360941586, "grad_norm": 1.2057806253433228, "learning_rate": 1.0949330227140361e-05, "loss": 0.327, "step": 1535 }, { "epoch": 2.6765475152571927, "grad_norm": 1.0908318758010864, "learning_rate": 1.0891089108910891e-05, "loss": 0.3349, "step": 1536 }, { "epoch": 2.678291194420227, "grad_norm": 1.0069559812545776, "learning_rate": 1.0832847990681422e-05, "loss": 0.3167, "step": 1537 }, { "epoch": 2.680034873583261, "grad_norm": 1.4272347688674927, "learning_rate": 1.0774606872451952e-05, "loss": 0.3721, "step": 1538 }, { "epoch": 2.6817785527462945, "grad_norm": 1.1538631916046143, "learning_rate": 1.0716365754222482e-05, "loss": 0.4044, "step": 1539 }, { "epoch": 2.6835222319093286, "grad_norm": 1.1878114938735962, "learning_rate": 1.065812463599301e-05, "loss": 0.3705, "step": 1540 }, { "epoch": 2.6852659110723627, "grad_norm": 1.7395167350769043, "learning_rate": 1.0599883517763541e-05, "loss": 0.4858, "step": 1541 }, { "epoch": 2.6870095902353968, "grad_norm": 1.0841209888458252, "learning_rate": 1.0541642399534071e-05, "loss": 0.3591, "step": 1542 }, { "epoch": 2.688753269398431, "grad_norm": 1.5711382627487183, "learning_rate": 1.0483401281304602e-05, "loss": 0.3216, "step": 1543 }, { "epoch": 2.6904969485614645, "grad_norm": 1.278748631477356, "learning_rate": 1.0425160163075132e-05, "loss": 0.3766, "step": 1544 }, { "epoch": 2.6922406277244986, "grad_norm": 1.4009778499603271, "learning_rate": 1.0366919044845662e-05, "loss": 0.3964, "step": 1545 }, { "epoch": 2.6939843068875327, "grad_norm": 1.452083706855774, "learning_rate": 1.0308677926616193e-05, "loss": 0.3873, "step": 1546 }, { "epoch": 2.6957279860505667, "grad_norm": 1.517400860786438, "learning_rate": 1.0250436808386721e-05, "loss": 0.4389, "step": 1547 }, { "epoch": 2.697471665213601, "grad_norm": 0.9959104657173157, "learning_rate": 1.0192195690157252e-05, "loss": 0.3473, "step": 1548 }, { "epoch": 2.6992153443766345, "grad_norm": 1.3751647472381592, "learning_rate": 1.0133954571927782e-05, "loss": 0.3713, "step": 1549 }, { "epoch": 2.7009590235396685, "grad_norm": 1.1045438051223755, "learning_rate": 1.0075713453698312e-05, "loss": 0.3874, "step": 1550 }, { "epoch": 2.7027027027027026, "grad_norm": 1.7028378248214722, "learning_rate": 1.0017472335468842e-05, "loss": 0.4377, "step": 1551 }, { "epoch": 2.7044463818657367, "grad_norm": 1.1359541416168213, "learning_rate": 9.959231217239371e-06, "loss": 0.3506, "step": 1552 }, { "epoch": 2.706190061028771, "grad_norm": 1.2454171180725098, "learning_rate": 9.900990099009901e-06, "loss": 0.4109, "step": 1553 }, { "epoch": 2.7079337401918044, "grad_norm": 0.9432161450386047, "learning_rate": 9.842748980780432e-06, "loss": 0.3222, "step": 1554 }, { "epoch": 2.709677419354839, "grad_norm": 0.9398223757743835, "learning_rate": 9.78450786255096e-06, "loss": 0.3112, "step": 1555 }, { "epoch": 2.7114210985178726, "grad_norm": 1.4244015216827393, "learning_rate": 9.72626674432149e-06, "loss": 0.4461, "step": 1556 }, { "epoch": 2.7131647776809067, "grad_norm": 1.1822954416275024, "learning_rate": 9.66802562609202e-06, "loss": 0.3313, "step": 1557 }, { "epoch": 2.7149084568439408, "grad_norm": 1.3621602058410645, "learning_rate": 9.609784507862551e-06, "loss": 0.3657, "step": 1558 }, { "epoch": 2.716652136006975, "grad_norm": 1.0615116357803345, "learning_rate": 9.551543389633081e-06, "loss": 0.3191, "step": 1559 }, { "epoch": 2.718395815170009, "grad_norm": 1.3279306888580322, "learning_rate": 9.493302271403612e-06, "loss": 0.389, "step": 1560 }, { "epoch": 2.7201394943330426, "grad_norm": 1.2821838855743408, "learning_rate": 9.435061153174142e-06, "loss": 0.4003, "step": 1561 }, { "epoch": 2.7218831734960767, "grad_norm": 1.389957070350647, "learning_rate": 9.37682003494467e-06, "loss": 0.3782, "step": 1562 }, { "epoch": 2.7236268526591108, "grad_norm": 1.1686240434646606, "learning_rate": 9.318578916715201e-06, "loss": 0.3735, "step": 1563 }, { "epoch": 2.725370531822145, "grad_norm": 0.9466689825057983, "learning_rate": 9.260337798485731e-06, "loss": 0.3071, "step": 1564 }, { "epoch": 2.727114210985179, "grad_norm": 1.338486909866333, "learning_rate": 9.202096680256262e-06, "loss": 0.3818, "step": 1565 }, { "epoch": 2.7288578901482126, "grad_norm": 0.9654226899147034, "learning_rate": 9.143855562026792e-06, "loss": 0.3008, "step": 1566 }, { "epoch": 2.7306015693112466, "grad_norm": 1.2418898344039917, "learning_rate": 9.085614443797322e-06, "loss": 0.3637, "step": 1567 }, { "epoch": 2.7323452484742807, "grad_norm": 1.1168924570083618, "learning_rate": 9.027373325567852e-06, "loss": 0.3819, "step": 1568 }, { "epoch": 2.734088927637315, "grad_norm": 1.182864785194397, "learning_rate": 8.969132207338381e-06, "loss": 0.3656, "step": 1569 }, { "epoch": 2.735832606800349, "grad_norm": 1.5129718780517578, "learning_rate": 8.910891089108911e-06, "loss": 0.3716, "step": 1570 }, { "epoch": 2.7375762859633825, "grad_norm": 1.2371889352798462, "learning_rate": 8.852649970879442e-06, "loss": 0.3765, "step": 1571 }, { "epoch": 2.7393199651264166, "grad_norm": 1.183395266532898, "learning_rate": 8.794408852649972e-06, "loss": 0.3582, "step": 1572 }, { "epoch": 2.7410636442894507, "grad_norm": 1.0342341661453247, "learning_rate": 8.736167734420502e-06, "loss": 0.2921, "step": 1573 }, { "epoch": 2.742807323452485, "grad_norm": 1.2161355018615723, "learning_rate": 8.677926616191031e-06, "loss": 0.3707, "step": 1574 }, { "epoch": 2.744551002615519, "grad_norm": 1.228370189666748, "learning_rate": 8.619685497961561e-06, "loss": 0.3602, "step": 1575 }, { "epoch": 2.7462946817785525, "grad_norm": 1.227278232574463, "learning_rate": 8.561444379732091e-06, "loss": 0.395, "step": 1576 }, { "epoch": 2.7480383609415866, "grad_norm": 1.0090162754058838, "learning_rate": 8.50320326150262e-06, "loss": 0.3506, "step": 1577 }, { "epoch": 2.7497820401046207, "grad_norm": 1.3225852251052856, "learning_rate": 8.44496214327315e-06, "loss": 0.4087, "step": 1578 }, { "epoch": 2.7515257192676548, "grad_norm": 1.1140888929367065, "learning_rate": 8.38672102504368e-06, "loss": 0.3239, "step": 1579 }, { "epoch": 2.753269398430689, "grad_norm": 1.3804244995117188, "learning_rate": 8.328479906814211e-06, "loss": 0.4269, "step": 1580 }, { "epoch": 2.7550130775937225, "grad_norm": 1.187097430229187, "learning_rate": 8.270238788584741e-06, "loss": 0.3467, "step": 1581 }, { "epoch": 2.756756756756757, "grad_norm": 1.2536342144012451, "learning_rate": 8.211997670355272e-06, "loss": 0.3718, "step": 1582 }, { "epoch": 2.7585004359197907, "grad_norm": 1.109397530555725, "learning_rate": 8.1537565521258e-06, "loss": 0.3354, "step": 1583 }, { "epoch": 2.7602441150828247, "grad_norm": 1.0016789436340332, "learning_rate": 8.09551543389633e-06, "loss": 0.2871, "step": 1584 }, { "epoch": 2.761987794245859, "grad_norm": 2.210793972015381, "learning_rate": 8.03727431566686e-06, "loss": 0.4811, "step": 1585 }, { "epoch": 2.763731473408893, "grad_norm": 1.2079439163208008, "learning_rate": 7.979033197437391e-06, "loss": 0.4363, "step": 1586 }, { "epoch": 2.765475152571927, "grad_norm": 1.1167229413986206, "learning_rate": 7.920792079207921e-06, "loss": 0.3393, "step": 1587 }, { "epoch": 2.7672188317349606, "grad_norm": 1.5805699825286865, "learning_rate": 7.862550960978452e-06, "loss": 0.4363, "step": 1588 }, { "epoch": 2.7689625108979947, "grad_norm": 1.70381760597229, "learning_rate": 7.804309842748982e-06, "loss": 0.4793, "step": 1589 }, { "epoch": 2.770706190061029, "grad_norm": 1.1999247074127197, "learning_rate": 7.746068724519512e-06, "loss": 0.3956, "step": 1590 }, { "epoch": 2.772449869224063, "grad_norm": 1.608633041381836, "learning_rate": 7.687827606290041e-06, "loss": 0.3978, "step": 1591 }, { "epoch": 2.774193548387097, "grad_norm": 1.0209282636642456, "learning_rate": 7.629586488060571e-06, "loss": 0.2997, "step": 1592 }, { "epoch": 2.7759372275501306, "grad_norm": 0.9929519295692444, "learning_rate": 7.571345369831101e-06, "loss": 0.3651, "step": 1593 }, { "epoch": 2.7776809067131647, "grad_norm": 1.0835473537445068, "learning_rate": 7.513104251601631e-06, "loss": 0.3428, "step": 1594 }, { "epoch": 2.779424585876199, "grad_norm": 1.1015191078186035, "learning_rate": 7.454863133372161e-06, "loss": 0.3314, "step": 1595 }, { "epoch": 2.781168265039233, "grad_norm": 1.0779227018356323, "learning_rate": 7.3966220151426916e-06, "loss": 0.3299, "step": 1596 }, { "epoch": 2.782911944202267, "grad_norm": 1.129568338394165, "learning_rate": 7.338380896913222e-06, "loss": 0.2977, "step": 1597 }, { "epoch": 2.7846556233653006, "grad_norm": 1.050660252571106, "learning_rate": 7.2801397786837505e-06, "loss": 0.2897, "step": 1598 }, { "epoch": 2.7863993025283347, "grad_norm": 1.173745036125183, "learning_rate": 7.221898660454281e-06, "loss": 0.3253, "step": 1599 }, { "epoch": 2.7881429816913688, "grad_norm": 1.2765098810195923, "learning_rate": 7.163657542224811e-06, "loss": 0.4496, "step": 1600 }, { "epoch": 2.789886660854403, "grad_norm": 1.1413556337356567, "learning_rate": 7.105416423995341e-06, "loss": 0.4057, "step": 1601 }, { "epoch": 2.791630340017437, "grad_norm": 1.0315749645233154, "learning_rate": 7.047175305765872e-06, "loss": 0.3794, "step": 1602 }, { "epoch": 2.7933740191804706, "grad_norm": 1.039086937904358, "learning_rate": 6.988934187536401e-06, "loss": 0.3103, "step": 1603 }, { "epoch": 2.7951176983435047, "grad_norm": 1.0060678720474243, "learning_rate": 6.9306930693069314e-06, "loss": 0.3365, "step": 1604 }, { "epoch": 2.7968613775065387, "grad_norm": 1.09319269657135, "learning_rate": 6.87245195107746e-06, "loss": 0.373, "step": 1605 }, { "epoch": 2.798605056669573, "grad_norm": 1.1891226768493652, "learning_rate": 6.81421083284799e-06, "loss": 0.396, "step": 1606 }, { "epoch": 2.800348735832607, "grad_norm": 1.0952730178833008, "learning_rate": 6.755969714618521e-06, "loss": 0.3415, "step": 1607 }, { "epoch": 2.8020924149956405, "grad_norm": 0.9881787300109863, "learning_rate": 6.697728596389051e-06, "loss": 0.2887, "step": 1608 }, { "epoch": 2.803836094158675, "grad_norm": 1.3834389448165894, "learning_rate": 6.639487478159581e-06, "loss": 0.3465, "step": 1609 }, { "epoch": 2.8055797733217087, "grad_norm": 1.4536134004592896, "learning_rate": 6.5812463599301115e-06, "loss": 0.3642, "step": 1610 }, { "epoch": 2.807323452484743, "grad_norm": 1.4343287944793701, "learning_rate": 6.523005241700642e-06, "loss": 0.4113, "step": 1611 }, { "epoch": 2.809067131647777, "grad_norm": 1.5979465246200562, "learning_rate": 6.4647641234711704e-06, "loss": 0.4152, "step": 1612 }, { "epoch": 2.810810810810811, "grad_norm": 1.1000953912734985, "learning_rate": 6.406523005241701e-06, "loss": 0.3694, "step": 1613 }, { "epoch": 2.812554489973845, "grad_norm": 1.4361798763275146, "learning_rate": 6.348281887012231e-06, "loss": 0.3861, "step": 1614 }, { "epoch": 2.8142981691368787, "grad_norm": 1.3240224123001099, "learning_rate": 6.2900407687827605e-06, "loss": 0.4097, "step": 1615 }, { "epoch": 2.8160418482999128, "grad_norm": 1.2052807807922363, "learning_rate": 6.231799650553291e-06, "loss": 0.3538, "step": 1616 }, { "epoch": 2.817785527462947, "grad_norm": 1.4145135879516602, "learning_rate": 6.173558532323821e-06, "loss": 0.3932, "step": 1617 }, { "epoch": 2.819529206625981, "grad_norm": 0.9427053332328796, "learning_rate": 6.1153174140943506e-06, "loss": 0.3375, "step": 1618 }, { "epoch": 2.821272885789015, "grad_norm": 1.0761576890945435, "learning_rate": 6.057076295864881e-06, "loss": 0.3461, "step": 1619 }, { "epoch": 2.8230165649520487, "grad_norm": 1.0317453145980835, "learning_rate": 5.998835177635411e-06, "loss": 0.3538, "step": 1620 }, { "epoch": 2.8247602441150828, "grad_norm": 1.241713523864746, "learning_rate": 5.940594059405941e-06, "loss": 0.3898, "step": 1621 }, { "epoch": 2.826503923278117, "grad_norm": 1.0854169130325317, "learning_rate": 5.882352941176471e-06, "loss": 0.3429, "step": 1622 }, { "epoch": 2.828247602441151, "grad_norm": 1.2828373908996582, "learning_rate": 5.824111822947001e-06, "loss": 0.3498, "step": 1623 }, { "epoch": 2.829991281604185, "grad_norm": 1.186730980873108, "learning_rate": 5.7658707047175315e-06, "loss": 0.3296, "step": 1624 }, { "epoch": 2.8317349607672186, "grad_norm": 1.1161404848098755, "learning_rate": 5.707629586488061e-06, "loss": 0.3114, "step": 1625 }, { "epoch": 2.8334786399302527, "grad_norm": 1.0869145393371582, "learning_rate": 5.6493884682585904e-06, "loss": 0.3114, "step": 1626 }, { "epoch": 2.835222319093287, "grad_norm": 1.1422297954559326, "learning_rate": 5.591147350029121e-06, "loss": 0.3451, "step": 1627 }, { "epoch": 2.836965998256321, "grad_norm": 1.1597990989685059, "learning_rate": 5.53290623179965e-06, "loss": 0.3483, "step": 1628 }, { "epoch": 2.838709677419355, "grad_norm": 1.5319658517837524, "learning_rate": 5.4746651135701805e-06, "loss": 0.3841, "step": 1629 }, { "epoch": 2.8404533565823886, "grad_norm": 1.1010382175445557, "learning_rate": 5.416423995340711e-06, "loss": 0.2776, "step": 1630 }, { "epoch": 2.8421970357454227, "grad_norm": 1.0903797149658203, "learning_rate": 5.358182877111241e-06, "loss": 0.303, "step": 1631 }, { "epoch": 2.843940714908457, "grad_norm": 1.1730499267578125, "learning_rate": 5.2999417588817705e-06, "loss": 0.3819, "step": 1632 }, { "epoch": 2.845684394071491, "grad_norm": 1.1266965866088867, "learning_rate": 5.241700640652301e-06, "loss": 0.3643, "step": 1633 }, { "epoch": 2.847428073234525, "grad_norm": 1.3036541938781738, "learning_rate": 5.183459522422831e-06, "loss": 0.3909, "step": 1634 }, { "epoch": 2.8491717523975586, "grad_norm": 1.5938457250595093, "learning_rate": 5.125218404193361e-06, "loss": 0.4901, "step": 1635 }, { "epoch": 2.850915431560593, "grad_norm": 1.659570336341858, "learning_rate": 5.066977285963891e-06, "loss": 0.4191, "step": 1636 }, { "epoch": 2.8526591107236268, "grad_norm": 1.167501449584961, "learning_rate": 5.008736167734421e-06, "loss": 0.3416, "step": 1637 }, { "epoch": 2.854402789886661, "grad_norm": 0.9935450553894043, "learning_rate": 4.950495049504951e-06, "loss": 0.3347, "step": 1638 }, { "epoch": 2.856146469049695, "grad_norm": 1.3904038667678833, "learning_rate": 4.89225393127548e-06, "loss": 0.4073, "step": 1639 }, { "epoch": 2.857890148212729, "grad_norm": 1.0988600254058838, "learning_rate": 4.83401281304601e-06, "loss": 0.3181, "step": 1640 }, { "epoch": 2.859633827375763, "grad_norm": 0.9747666716575623, "learning_rate": 4.775771694816541e-06, "loss": 0.3054, "step": 1641 }, { "epoch": 2.8613775065387967, "grad_norm": 0.9514352679252625, "learning_rate": 4.717530576587071e-06, "loss": 0.28, "step": 1642 }, { "epoch": 2.863121185701831, "grad_norm": 1.1461741924285889, "learning_rate": 4.6592894583576005e-06, "loss": 0.3371, "step": 1643 }, { "epoch": 2.864864864864865, "grad_norm": 1.1800577640533447, "learning_rate": 4.601048340128131e-06, "loss": 0.3607, "step": 1644 }, { "epoch": 2.866608544027899, "grad_norm": 1.0969974994659424, "learning_rate": 4.542807221898661e-06, "loss": 0.327, "step": 1645 }, { "epoch": 2.868352223190933, "grad_norm": 1.4357918500900269, "learning_rate": 4.4845661036691905e-06, "loss": 0.2807, "step": 1646 }, { "epoch": 2.8700959023539667, "grad_norm": 1.2677643299102783, "learning_rate": 4.426324985439721e-06, "loss": 0.379, "step": 1647 }, { "epoch": 2.871839581517001, "grad_norm": 1.5781984329223633, "learning_rate": 4.368083867210251e-06, "loss": 0.4648, "step": 1648 }, { "epoch": 2.873583260680035, "grad_norm": 1.7117245197296143, "learning_rate": 4.309842748980781e-06, "loss": 0.5205, "step": 1649 }, { "epoch": 2.875326939843069, "grad_norm": 1.4843841791152954, "learning_rate": 4.25160163075131e-06, "loss": 0.4183, "step": 1650 }, { "epoch": 2.877070619006103, "grad_norm": 0.9890002012252808, "learning_rate": 4.19336051252184e-06, "loss": 0.277, "step": 1651 }, { "epoch": 2.8788142981691367, "grad_norm": 1.119205355644226, "learning_rate": 4.135119394292371e-06, "loss": 0.3592, "step": 1652 }, { "epoch": 2.880557977332171, "grad_norm": 1.5379915237426758, "learning_rate": 4.0768782760629e-06, "loss": 0.4474, "step": 1653 }, { "epoch": 2.882301656495205, "grad_norm": 1.2695070505142212, "learning_rate": 4.01863715783343e-06, "loss": 0.3676, "step": 1654 }, { "epoch": 2.884045335658239, "grad_norm": 1.1871687173843384, "learning_rate": 3.960396039603961e-06, "loss": 0.3649, "step": 1655 }, { "epoch": 2.885789014821273, "grad_norm": 1.1970678567886353, "learning_rate": 3.902154921374491e-06, "loss": 0.3478, "step": 1656 }, { "epoch": 2.8875326939843067, "grad_norm": 1.555076241493225, "learning_rate": 3.8439138031450205e-06, "loss": 0.443, "step": 1657 }, { "epoch": 2.8892763731473408, "grad_norm": 1.3076199293136597, "learning_rate": 3.7856726849155503e-06, "loss": 0.3955, "step": 1658 }, { "epoch": 2.891020052310375, "grad_norm": 1.4237587451934814, "learning_rate": 3.7274315666860806e-06, "loss": 0.4497, "step": 1659 }, { "epoch": 2.892763731473409, "grad_norm": 1.2759581804275513, "learning_rate": 3.669190448456611e-06, "loss": 0.3981, "step": 1660 }, { "epoch": 2.894507410636443, "grad_norm": 1.3208640813827515, "learning_rate": 3.6109493302271404e-06, "loss": 0.391, "step": 1661 }, { "epoch": 2.8962510897994767, "grad_norm": 1.8538367748260498, "learning_rate": 3.5527082119976707e-06, "loss": 0.4722, "step": 1662 }, { "epoch": 2.8979947689625107, "grad_norm": 1.1601651906967163, "learning_rate": 3.4944670937682006e-06, "loss": 0.3492, "step": 1663 }, { "epoch": 2.899738448125545, "grad_norm": 1.1292155981063843, "learning_rate": 3.43622597553873e-06, "loss": 0.3641, "step": 1664 }, { "epoch": 2.901482127288579, "grad_norm": 0.8957279920578003, "learning_rate": 3.3779848573092603e-06, "loss": 0.2636, "step": 1665 }, { "epoch": 2.903225806451613, "grad_norm": 1.1692099571228027, "learning_rate": 3.3197437390797906e-06, "loss": 0.3062, "step": 1666 }, { "epoch": 2.9049694856146466, "grad_norm": 1.2690669298171997, "learning_rate": 3.261502620850321e-06, "loss": 0.3731, "step": 1667 }, { "epoch": 2.906713164777681, "grad_norm": 1.1703300476074219, "learning_rate": 3.2032615026208504e-06, "loss": 0.3582, "step": 1668 }, { "epoch": 2.908456843940715, "grad_norm": 1.3223083019256592, "learning_rate": 3.1450203843913803e-06, "loss": 0.3573, "step": 1669 }, { "epoch": 2.910200523103749, "grad_norm": 1.072405457496643, "learning_rate": 3.0867792661619106e-06, "loss": 0.2942, "step": 1670 }, { "epoch": 2.911944202266783, "grad_norm": 1.3584511280059814, "learning_rate": 3.0285381479324404e-06, "loss": 0.4678, "step": 1671 }, { "epoch": 2.913687881429817, "grad_norm": 1.1214185953140259, "learning_rate": 2.9702970297029703e-06, "loss": 0.2859, "step": 1672 }, { "epoch": 2.915431560592851, "grad_norm": 1.0456745624542236, "learning_rate": 2.9120559114735006e-06, "loss": 0.3478, "step": 1673 }, { "epoch": 2.9171752397558848, "grad_norm": 1.2242815494537354, "learning_rate": 2.8538147932440305e-06, "loss": 0.3268, "step": 1674 }, { "epoch": 2.918918918918919, "grad_norm": 1.056156039237976, "learning_rate": 2.7955736750145604e-06, "loss": 0.3238, "step": 1675 }, { "epoch": 2.920662598081953, "grad_norm": 1.2081284523010254, "learning_rate": 2.7373325567850902e-06, "loss": 0.4206, "step": 1676 }, { "epoch": 2.922406277244987, "grad_norm": 1.3264400959014893, "learning_rate": 2.6790914385556205e-06, "loss": 0.3315, "step": 1677 }, { "epoch": 2.924149956408021, "grad_norm": 1.2248051166534424, "learning_rate": 2.6208503203261504e-06, "loss": 0.3964, "step": 1678 }, { "epoch": 2.9258936355710548, "grad_norm": 1.4145220518112183, "learning_rate": 2.5626092020966803e-06, "loss": 0.4132, "step": 1679 }, { "epoch": 2.927637314734089, "grad_norm": 1.4195261001586914, "learning_rate": 2.5043680838672106e-06, "loss": 0.3916, "step": 1680 }, { "epoch": 2.929380993897123, "grad_norm": 1.3782941102981567, "learning_rate": 2.44612696563774e-06, "loss": 0.3937, "step": 1681 }, { "epoch": 2.931124673060157, "grad_norm": 1.4571857452392578, "learning_rate": 2.3878858474082704e-06, "loss": 0.4079, "step": 1682 }, { "epoch": 2.932868352223191, "grad_norm": 1.3620902299880981, "learning_rate": 2.3296447291788002e-06, "loss": 0.3638, "step": 1683 }, { "epoch": 2.9346120313862247, "grad_norm": 1.3715851306915283, "learning_rate": 2.2714036109493305e-06, "loss": 0.3705, "step": 1684 }, { "epoch": 2.936355710549259, "grad_norm": 1.6919398307800293, "learning_rate": 2.2131624927198604e-06, "loss": 0.4665, "step": 1685 }, { "epoch": 2.938099389712293, "grad_norm": 1.75352144241333, "learning_rate": 2.1549213744903903e-06, "loss": 0.4104, "step": 1686 }, { "epoch": 2.939843068875327, "grad_norm": 1.368252158164978, "learning_rate": 2.09668025626092e-06, "loss": 0.3702, "step": 1687 }, { "epoch": 2.941586748038361, "grad_norm": 1.7968131303787231, "learning_rate": 2.03843913803145e-06, "loss": 0.4734, "step": 1688 }, { "epoch": 2.9433304272013947, "grad_norm": 1.2275371551513672, "learning_rate": 1.9801980198019803e-06, "loss": 0.3706, "step": 1689 }, { "epoch": 2.945074106364429, "grad_norm": 1.3560543060302734, "learning_rate": 1.9219569015725102e-06, "loss": 0.3827, "step": 1690 }, { "epoch": 2.946817785527463, "grad_norm": 1.1091704368591309, "learning_rate": 1.8637157833430403e-06, "loss": 0.3296, "step": 1691 }, { "epoch": 2.948561464690497, "grad_norm": 1.138864517211914, "learning_rate": 1.8054746651135702e-06, "loss": 0.3524, "step": 1692 }, { "epoch": 2.950305143853531, "grad_norm": 1.5542616844177246, "learning_rate": 1.7472335468841003e-06, "loss": 0.3774, "step": 1693 }, { "epoch": 2.9520488230165647, "grad_norm": 1.2709039449691772, "learning_rate": 1.6889924286546302e-06, "loss": 0.3505, "step": 1694 }, { "epoch": 2.953792502179599, "grad_norm": 1.2946587800979614, "learning_rate": 1.6307513104251605e-06, "loss": 0.3694, "step": 1695 }, { "epoch": 2.955536181342633, "grad_norm": 1.2415968179702759, "learning_rate": 1.5725101921956901e-06, "loss": 0.3773, "step": 1696 }, { "epoch": 2.957279860505667, "grad_norm": 1.5554898977279663, "learning_rate": 1.5142690739662202e-06, "loss": 0.4114, "step": 1697 }, { "epoch": 2.959023539668701, "grad_norm": 1.165042757987976, "learning_rate": 1.4560279557367503e-06, "loss": 0.3626, "step": 1698 }, { "epoch": 2.960767218831735, "grad_norm": 1.2992208003997803, "learning_rate": 1.3977868375072802e-06, "loss": 0.3861, "step": 1699 }, { "epoch": 2.962510897994769, "grad_norm": 1.4234031438827515, "learning_rate": 1.3395457192778103e-06, "loss": 0.3858, "step": 1700 }, { "epoch": 2.964254577157803, "grad_norm": 1.559966802597046, "learning_rate": 1.2813046010483402e-06, "loss": 0.4234, "step": 1701 }, { "epoch": 2.965998256320837, "grad_norm": 1.1815698146820068, "learning_rate": 1.22306348281887e-06, "loss": 0.3039, "step": 1702 }, { "epoch": 2.967741935483871, "grad_norm": 1.1233311891555786, "learning_rate": 1.1648223645894001e-06, "loss": 0.3623, "step": 1703 }, { "epoch": 2.969485614646905, "grad_norm": 1.0716593265533447, "learning_rate": 1.1065812463599302e-06, "loss": 0.2781, "step": 1704 }, { "epoch": 2.971229293809939, "grad_norm": 1.4309786558151245, "learning_rate": 1.04834012813046e-06, "loss": 0.4352, "step": 1705 }, { "epoch": 2.972972972972973, "grad_norm": 1.2309136390686035, "learning_rate": 9.900990099009902e-07, "loss": 0.3673, "step": 1706 }, { "epoch": 2.974716652136007, "grad_norm": 1.605991005897522, "learning_rate": 9.318578916715202e-07, "loss": 0.4216, "step": 1707 }, { "epoch": 2.976460331299041, "grad_norm": 1.0290449857711792, "learning_rate": 8.736167734420501e-07, "loss": 0.3257, "step": 1708 }, { "epoch": 2.978204010462075, "grad_norm": 1.1093261241912842, "learning_rate": 8.153756552125802e-07, "loss": 0.3489, "step": 1709 }, { "epoch": 2.979947689625109, "grad_norm": 0.9543284177780151, "learning_rate": 7.571345369831101e-07, "loss": 0.3126, "step": 1710 }, { "epoch": 2.981691368788143, "grad_norm": 1.3305211067199707, "learning_rate": 6.988934187536401e-07, "loss": 0.3799, "step": 1711 }, { "epoch": 2.983435047951177, "grad_norm": 1.1349040269851685, "learning_rate": 6.406523005241701e-07, "loss": 0.3736, "step": 1712 }, { "epoch": 2.985178727114211, "grad_norm": 1.0682435035705566, "learning_rate": 5.824111822947001e-07, "loss": 0.3329, "step": 1713 }, { "epoch": 2.986922406277245, "grad_norm": 1.1914663314819336, "learning_rate": 5.2417006406523e-07, "loss": 0.3671, "step": 1714 }, { "epoch": 2.988666085440279, "grad_norm": 1.2272059917449951, "learning_rate": 4.659289458357601e-07, "loss": 0.314, "step": 1715 }, { "epoch": 2.9904097646033128, "grad_norm": 1.1411256790161133, "learning_rate": 4.076878276062901e-07, "loss": 0.3844, "step": 1716 }, { "epoch": 2.992153443766347, "grad_norm": 1.003071904182434, "learning_rate": 3.4944670937682005e-07, "loss": 0.3174, "step": 1717 }, { "epoch": 2.993897122929381, "grad_norm": 1.3839049339294434, "learning_rate": 2.9120559114735003e-07, "loss": 0.4214, "step": 1718 }, { "epoch": 2.995640802092415, "grad_norm": 1.3427358865737915, "learning_rate": 2.3296447291788004e-07, "loss": 0.3454, "step": 1719 }, { "epoch": 2.997384481255449, "grad_norm": 0.913419246673584, "learning_rate": 1.7472335468841002e-07, "loss": 0.3138, "step": 1720 }, { "epoch": 2.9991281604184827, "grad_norm": 1.1480063199996948, "learning_rate": 1.1648223645894002e-07, "loss": 0.3505, "step": 1721 }, { "epoch": 3.0, "grad_norm": 2.2225308418273926, "learning_rate": 5.824111822947001e-08, "loss": 0.4954, "step": 1722 } ], "logging_steps": 1, "max_steps": 1722, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.3774430541381996e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }